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

    Neuronpedia

    INDEX
    Explanations

    specific names and their associated contributions or statistics

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

    names and numbers in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.39
     “
    -0.38
    ...
    -0.38
     ...
    -0.38
    es
    -0.38
     We
    -0.37
    ↵↵
    -0.36
      
    -0.35
     The
    -0.35
    …
    -0.35
    POSITIVE LOGITS
     فريبيس
    0.80
     ब्रेकडाउन
    0.78
    URLException
    0.75
    ValueStyle
    0.74
    IVEREF
    0.73
    TargetException
    0.71
    MigrationBuilder
    0.71
    CloseOperation
    0.70
    TemporalType
    0.68
    StoreMessageInfo
    0.68
    Act Density 0.090%

    No Known Activations