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

    Neuronpedia

    INDEX
    Explanations

    HTTP methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ميع
    -0.07
     הנוכ
    -0.07
    讴
    -0.07
    FOUNDATION
    -0.06
     contentious
    -0.06
     excell
    -0.06
    Tracks
    -0.06
    菲律
    -0.06
     Uttar
    -0.06
    .Flush
    -0.06
    POSITIVE LOGITS
     {"
    0.07
     #"
    0.07
    _grp
    0.07
    ご利用
    0.07
    Voltage
    0.07
     compra
    0.07
    ynomial
    0.07
    걸
    0.07
    0.07
    专业
    0.07
    Act Density 0.003%

    No Known Activations