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

    Neuronpedia

    INDEX
    Explanations

    technical references and figures related to complex concepts

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

    referencing figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.56
    ConstraintMaker
    -0.54
     Wikime
    -0.54
    MockBean
    -0.51
     <<<<<<<<<<<<<<
    -0.51
    RTLD
    -0.50
    setVerticalGroup
    -0.48
    yarnpkg
    -0.47
    ModelAdmin
    -0.46
    annica
    -0.46
    POSITIVE LOGITS
    opsida
    0.45
     informée
    0.40
     ocur
    0.36
     apag
    0.35
    pantalón
    0.35
    Name
    0.33
     übri
    0.33
    text
    0.33
    tahankan
    0.33
    UnusedPrivate
    0.33
    Act Density 0.255%

    No Known Activations