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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Geoffrey
    -0.08
    emey
    -0.07
    PGA
    -0.06
     Oprah
    -0.06
    辆
    -0.06
     bychom
    -0.06
    AsStringAsync
    -0.06
    uyệ
    -0.06
    asant
    -0.06
     setbacks
    -0.06
    POSITIVE LOGITS
    =tf
    0.07
     hypothesis
    0.07
     [$
    0.06
    vw
    0.06
    aux
    0.06
     additionally
    0.06
    :h
    0.06
    stats
    0.06
    _vote
    0.06
    .patch
    0.06
    Act Density 0.009%

    No Known Activations