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

    Neuronpedia

    INDEX
    Explanations

    chess notation ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     |=
    0.35
    са
    0.35
    сы
    0.35
    sendPluginResult
    0.35
     поговори
    0.34
     blem
    0.34
    ርሃ
    0.33
    firmasi
    0.33
    barui
    0.33
    яви
    0.33
    POSITIVE LOGITS
    LIB
    0.40
     REST
    0.39
    ﺏ
    0.37
     LIB
    0.37
    ."],
    0.36
    냐면
    0.35
    丰
    0.35
    两位
    0.34
    麴
    0.34
     دفع
    0.33
    Act Density 0.001%

    No Known Activations