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

    Neuronpedia

    INDEX
    Explanations

    Nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hh
    -0.07
    velt
    -0.06
     университ
    -0.06
    BigInt
    -0.06
    _lhs
    -0.06
    941
    -0.06
    (<?
    -0.06
    _Speed
    -0.06
    ackson
    -0.06
    (||
    -0.06
    POSITIVE LOGITS
     Womens
    0.07
    unicipio
    0.07
     arous
    0.07
     signific
    0.06
     dependent
    0.06
    ッ
    0.06
    더니
    0.06
    SENS
    0.06
    Ơ
    0.06
     Automobile
    0.06
    Act Density 0.256%

    No Known Activations