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

    Neuronpedia

    INDEX
    Explanations

    buttons associated with user interactions and confirmations

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

    Actions like sending, voting, saving, and calculating

    np_acts-logits-general · gemini-2.0-flash

    action confirmation buttons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.77
     pinulongan
    -0.77
    awtextra
    -0.73
     ModelExpression
    -0.73
    rungsseite
    -0.73
    TestingModule
    -0.72
     ujednoznacz
    -0.72
     erſt
    -0.71
     BoxFit
    -0.71
    pecabe
    -0.71
    POSITIVE LOGITS
    ✭✭
    0.30
     autorytatywna
    0.29
     impress
    0.29
     immediately
    0.28
     senz
    0.27
     noten
    0.27
     save
    0.25
     liability
    0.24
     yes
    0.24
    >>
    0.24
    Act Density 0.120%

    No Known Activations