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

    Neuronpedia

    INDEX
    Explanations

    Customer service emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Push
    -0.07
    :::::
    -0.07
    ồm
    -0.07
    adors
    -0.06
    onaut
    -0.06
     bleak
    -0.06
    /DTD
    -0.06
     Slam
    -0.06
     THPT
    -0.06
    ulers
    -0.06
    POSITIVE LOGITS
    變
    0.07
    =args
    0.06
     planta
    0.06
    .Annotation
    0.06
    _difference
    0.06
    .ex
    0.06
    .ke
    0.06
    .ad
    0.06
    ar
    0.06
    _coordinate
    0.06
    Act Density 0.030%

    No Known Activations