Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to systems and processes involving examinations or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Specific roles, tasks, or instructions

    np_acts-logits-general · gemini-2.0-flash

    Agent, facility, units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لينكات
    -0.41
    huriyet
    -0.37
    mişti
    -0.37
    MethodManager
    -0.36
     OFDb
    -0.35
    Portail
    -0.34
    verwijspagina
    -0.33
    Educación
    -0.33
    enumii
    -0.33
    Hochspringen
    -0.33
    POSITIVE LOGITS
    FunctionFlags
    0.47
    arParams
    0.47
     SCP
    0.44
    ValueStyle
    0.44
     humanity
    0.43
     autorytatywna
    0.42
     defaultstate
    0.42
    transQ
    0.41
     CommonModule
    0.41
    IntoConstraints
    0.41
    Act Density 1.415%

    No Known Activations