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

    Neuronpedia

    INDEX
    Explanations

    Pr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     movable
    -0.07
     followers
    -0.07
    (alert
    -0.06
     آل
    -0.06
    ,U
    -0.06
     Sullivan
    -0.06
    covering
    -0.06
     яку
    -0.06
    .download
    -0.06
    _area
    -0.06
    POSITIVE LOGITS
     Printable
    0.07
     영상
    0.07
    مح
    0.07
     �
    0.06
    prove
    0.06
    -lnd
    0.06
    μή
    0.06
     січня
    0.06
     rogue
    0.06
    ็ค
    0.06
    Act Density 0.004%

    No Known Activations