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

    Neuronpedia

    INDEX
    Explanations

    References and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collage
    -0.07
    новаж
    -0.07
    -bars
    -0.06
     collider
    -0.06
     amendment
    -0.06
    +w
    -0.06
     mold
    -0.06
    ":↵
    -0.06
    ':↵
    -0.06
     cyclic
    -0.06
    POSITIVE LOGITS
    ザー
    0.07
     mListener
    0.06
    .getLogin
    0.06
    _MODULE
    0.06
     Aux
    0.06
     سعود
    0.06
    (INT
    0.06
     intelligent
    0.06
    ipop
    0.06
    plor
    0.06
    Act Density 0.019%

    No Known Activations