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

    Neuronpedia

    INDEX
    Explanations

    business/advice context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    に乗
    -0.07
    丈夫
    -0.07
    _setting
    -0.07
     entren
    -0.07
    짢
    -0.07
    版
    -0.07
    trzym
    -0.07
    扶
    -0.07
    選
    -0.07
    Character
    -0.07
    POSITIVE LOGITS
    =?";↵
    0.08
     SAS
    0.08
     ox
    0.07
    tatus
    0.07
     XC
    0.07
     BOOK
    0.07
     Gore
    0.06
     complexities
    0.06
     echoing
    0.06
    cas
    0.06
    Act Density 0.092%

    No Known Activations