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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拜
    -0.07
     Ang
    -0.07
    股东
    -0.07
     respectfully
    -0.07
     Won
    -0.07
     What
    -0.07
     exploring
    -0.07
    _bn
    -0.07
    nett
    -0.07
    的角度
    -0.07
    POSITIVE LOGITS
    转基因
    0.07
    แฮ
    0.07
     factura
    0.07
     levy
    0.06
    医院
    0.06
     Electric
    0.06
     downright
    0.06
    ="""
    0.06
    .persist
    0.06
     Duis
    0.06
    Act Density 0.004%

    No Known Activations