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

    Neuronpedia

    INDEX
    Explanations

    terms related to counting or categorization

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

    卡牌、江木、arctan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -------
    -0.50
     Tratado
    -0.48
    ouer
    -0.47
    ers
    -0.44
     saites
    -0.43
    stood
    -0.43
    Архівовано
    -0.42
    splitlines
    -0.42
     journaux
    -0.41
    Tikang
    -0.41
    POSITIVE LOGITS
     ка
    1.70
    Ка
    1.24
     Ка
    1.21
    ка
    0.86
    カ
    0.84
     Ka
    0.83
     카
    0.81
    卡
    0.78
     κα
    0.75
     КА
    0.75
    Act Density 0.001%

    No Known Activations