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

    Neuronpedia

    INDEX
    Explanations

    Code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंभ
    -0.07
     attraction
    -0.07
    λυ
    -0.07
    ivol
    -0.06
     Τζ
    -0.06
    이나
    -0.06
    ίου
    -0.06
    _sprites
    -0.06
     rout
    -0.06
    直播
    -0.06
    POSITIVE LOGITS
    training
    0.08
    .getFullYear
    0.08
    .HashMap
    0.08
     Observation
    0.07
     Gör
    0.07
    νονται
    0.07
     whore
    0.06
     Sche
    0.06
    nThe
    0.06
     Chic
    0.06
    Act Density 0.000%

    No Known Activations