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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UMB
    -0.07
     رح
    -0.07
    ीछ
    -0.06
    ion
    -0.06
    _cou
    -0.06
    aps
    -0.06
     ghi
    -0.06
    ौं
    -0.06
    =response
    -0.06
    <s
    -0.06
    POSITIVE LOGITS
     Blocking
    0.07
    (prediction
    0.07
     enduring
    0.06
    .boolean
    0.06
     Bian
    0.06
     çerçev
    0.06
    .touch
    0.06
    قات
    0.06
    üh
    0.06
    _baseline
    0.06
    Act Density 0.194%

    No Known Activations