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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating confirmation or agreement

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

    Japanese sentence-ending explanation/confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chooser
    -0.50
     Roskov
    -0.48
    Біографія
    -0.48
     Comprom
    -0.48
    ContentAlignment
    -0.48
     bef
    -0.47
    ьаж
    -0.47
    UserScript
    -0.46
    propor
    -0.46
    DataPropertyName
    -0.46
    POSITIVE LOGITS
     asalto
    0.54
     preuves
    0.52
     réactions
    0.51
     Aufstieg
    0.51
     présidenti
    0.50
    เยอะ
    0.49
     nächsten
    0.49
     attaques
    0.48
     vermelhas
    0.48
     immédi
    0.48
    Act Density 0.000%

    No Known Activations