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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    つい
    -0.07
     ascend
    -0.07
    应聘
    -0.07
     prend
    -0.07
    Pacific
    -0.07
    Begin
    -0.07
    requested
    -0.07
    ]),
    -0.07
     entend
    -0.07
    电子邮件
    -0.06
    POSITIVE LOGITS
    煜
    0.07
    .rate
    0.07
    (cal
    0.07
     quot
    0.07
    _Metadata
    0.06
     rate
    0.06
    步伐
    0.06
    uil
    0.06
    inherits
    0.06
    plans
    0.06
    Act Density 0.023%

    No Known Activations