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

    Neuronpedia

    INDEX
    Explanations

    row

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -exc
    -0.07
    *k
    -0.07
    Gradient
    -0.07
     µ
    -0.06
     xp
    -0.06
     Hundred
    -0.06
     h
    -0.06
    Kel
    -0.06
    _bar
    -0.06
    sj
    -0.06
    POSITIVE LOGITS
     Moines
    0.07
    ไทย
    0.06
     легко
    0.06
     Knoxville
    0.06
    gb
    0.06
     @{$
    0.06
    ุณ
    0.06
    gregated
    0.06
    (QL
    0.06
    Cont
    0.06
    Act Density 0.039%

    No Known Activations