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

    Neuronpedia

    INDEX
    Explanations

    WW

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     daycare
    -0.06
     KD
    -0.06
     LD
    -0.06
     NV
    -0.06
    andard
    -0.06
    rna
    -0.06
    -red
    -0.06
     serialization
    -0.06
     unconventional
    -0.06
     SUV
    -0.06
    POSITIVE LOGITS
     +
↵
    0.07
    '];
↵
    0.07
    .BO
    0.07
    ΑΚ
    0.06
    ('
    0.06
    =('
    0.06
     Alzheimer
    0.06
     بازیگر
    0.06
    ,__
    0.06
     caste
    0.06
    Act Density 0.052%

    No Known Activations