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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Item
    -0.07
    meleri
    -0.06
    mts
    -0.06
    titulo
    -0.06
    ulario
    -0.06
    ením
    -0.06
    Addr
    -0.06
    estado
    -0.06
     млн
    -0.06
     трен
    -0.06
    POSITIVE LOGITS
     JADX
    0.07
    647
    0.06
    �
    0.06
     LOG
    0.06
    중에
    0.06
     색
    0.06
    ONGL
    0.06
     YE
    0.06
    เกษ
    0.06
     discourse
    0.06
    Act Density 0.028%

    No Known Activations