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

    Neuronpedia

    INDEX
    Explanations

    theme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🍒
    -0.08
    (ix
    -0.07
    _TILE
    -0.07
     Williamson
    -0.07
    _Pin
    -0.07
    力还是
    -0.07
    鹝
    -0.06
     Executive
    -0.06
    liqu
    -0.06
    _imm
    -0.06
    POSITIVE LOGITS
     songs
    0.07
    .hero
    0.07
     Kafka
    0.07
    memo
    0.07
     authorization
    0.07
     אחרונים
    0.07
    requency
    0.06
    ᔭ
    0.06
    .configureTestingModule
    0.06
    Mongo
    0.06
    Act Density 0.007%

    No Known Activations