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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making and changes in plans or schedules

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

    verbs followed by key phrase elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Werdegang
    -0.44
    Портал
    -0.39
    rungsseite
    -0.38
    AddAttribute
    -0.38
    optionalTypeArgs
    -0.37
    DockStyle
    -0.36
     CreateTagHelper
    -0.36
     autorytatywna
    -0.36
    tagHelperRunner
    -0.35
     Wagner
    -0.35
    POSITIVE LOGITS
     indefinitely
    0.56
    ſelves
    0.51
     contextLoads
    0.50
    ftance
    0.48
     itinéraires
    0.47
    ouncements
    0.47
    ſelf
    0.46
     iyong
    0.45
     gynnwys
    0.45
    대로
    0.43
    Act Density 0.005%

    No Known Activations