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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Retrofit
    -0.08
    _dx
    -0.08
    duction
    -0.07
    (panel
    -0.07
    )V
    -0.07
     האדם
    -0.07
    >"+
    -0.07
    ONSE
    -0.06
     pretext
    -0.06
     Incident
    -0.06
    POSITIVE LOGITS
    ãng
    0.07
    eliac
    0.07
    -cancel
    0.06
     (�
    0.06
    .wikipedia
    0.06
    쌍
    0.06
    =((
    0.06
    鄂
    0.06
     mayo
    0.06
    ()?>
    0.06
    Act Density 0.001%

    No Known Activations