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

    Neuronpedia

    INDEX
    Explanations

    int

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Grad
    -0.06
    rink
    -0.06
     Closing
    -0.06
     Ridge
    -0.06
    father
    -0.06
     Former
    -0.06
    .Contracts
    -0.06
    _Property
    -0.06
    Kh
    -0.06
     accesses
    -0.06
    POSITIVE LOGITS
    /pi
    0.08
    <Customer
    0.07
    での
    0.07
    �
    0.07
    лок
    0.06
    .AutoScaleMode
    0.06
    ่าค
    0.06
    imension
    0.06
    ji
    0.06
    (mask
    0.06
    Act Density 0.015%

    No Known Activations