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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    
    -0.76
    NameInMap
    -0.71
     oprot
    -0.70
     Chwiliwch
    -0.67
    endous
    -0.66
    }`}>
    -0.65
    存于互联网档案馆
    -0.64
     Audiodateien
    -0.63
     ?>/
    -0.62
    hydra
    -0.61
    POSITIVE LOGITS
    CharField
    0.53
    <bos>
    0.42
     college
    0.40
     ручки
    0.38
     NLI
    0.38
     Canadian
    0.37
     of
    0.37
     displaced
    0.36
    lagt
    0.35
    Ecc
    0.35
    Act Density 0.009%

    No Known Activations