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

    Neuronpedia

    INDEX
    Explanations

    document extracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *v
    -0.08
    toHaveBeenCalledWith
    -0.07
    anganese
    -0.07
    (Collision
    -0.06
     Крім
    -0.06
    326
    -0.06
    平方
    -0.06
    iswa
    -0.06
    adan
    -0.06
    -slider
    -0.06
    POSITIVE LOGITS
    MENT
    0.08
     �
    0.07
     mec
    0.07
    Clock
    0.06
    ments
    0.06
    <p
    0.06
    Off
    0.06
     پزشکی
    0.06
     anderen
    0.06
    LING
    0.06
    Act Density 0.000%

    No Known Activations