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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    when
    -0.07
     after
    -0.07
     dl
    -0.06
     productions
    -0.06
     After
    -0.06
    Threshold
    -0.06
    خی
    -0.06
    Si
    -0.06
     threshold
    -0.06
    -faced
    -0.06
    POSITIVE LOGITS
    .NoSuch
    0.08
     روابط
    0.07
    .BatchNorm
    0.06
     opráv
    0.06
     stør
    0.06
    .SizeMode
    0.06
    istung
    0.06
    .JSONException
    0.06
    ู้
    0.06
    _BEGIN
    0.06
    Act Density 0.041%

    No Known Activations