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

    Neuronpedia

    INDEX
    Explanations

    open a terminal or command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑠
    0.82
     하나의
    0.80
     Airplane
    0.80
    stoke
    0.79
    openai
    0.79
    Tabla
    0.79
     Tradu
    0.79
     Satz
    0.77
     над
    0.77
    𝑎
    0.76
    POSITIVE LOGITS
    קים
    0.81
     everything
    0.79
    irdiği
    0.79
    亓
    0.76
    ayaran
    0.76
     সংরক্ষিত
    0.75
    ゴン
    0.75
    ﹗
    0.74
    鰭
    0.74
    చిన
    0.74
    Act Density 0.010%

    No Known Activations