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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns/Possible names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .count
    -0.08
    İK
    -0.07
    Connell
    -0.07
     così
    -0.07
     Feb
    -0.07
    芝
    -0.07
    ⁻
    -0.07
    BLACK
    -0.06
     ecx
    -0.06
    abd
    -0.06
    POSITIVE LOGITS
    装修公司
    0.07
     breed
    0.07
     visibly
    0.07
    .Toast
    0.07
    不惜
    0.07
     outlier
    0.07
    .material
    0.07
     travellers
    0.07
    _gl
    0.07
    property
    0.07
    Act Density 0.254%

    No Known Activations