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

    Neuronpedia

    INDEX
    Explanations

    specifications or characteristics related to formatting and graphical elements

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

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.72
    Vidite
    -0.70
    TargetException
    -0.67
     Италијани
    -0.65
    IsMutable
    -0.63
     informée
    -0.61
     <>",
    -0.60
     виправивши
    -0.60
    tagHelperRunner
    -0.59
     autorytatywna
    -0.55
    POSITIVE LOGITS
    WithIdentifier
    0.40
     Apare
    0.37
     Dmit
    0.36
    ConstraintMaker
    0.36
    ană
    0.35
    ⇛
    0.34
    pflicht
    0.33
     Persson
    0.33
    EMPT
    0.33
     mệnh
    0.32
    Act Density 0.193%

    No Known Activations