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

    Neuronpedia

    INDEX
    Explanations

    requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getchar
    -0.07
    千方
    -0.07
     ontvangst
    -0.07
     strategically
    -0.07
    .GetChild
    -0.07
     глав
    -0.07
    变更
    -0.07
     đóng
    -0.07
    福田
    -0.06
    煓
    -0.06
    POSITIVE LOGITS
    noticed
    0.08
    랄
    0.08
     рекл
    0.07
    _modified
    0.07
     ################################################################
    0.07
    Analy
    0.07
     noticeable
    0.07
    🚲
    0.07
    lève
    0.07
    ("\"
    0.07
    Act Density 0.005%

    No Known Activations