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

    Neuronpedia

    INDEX
    Explanations

    websites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    인트
    -0.07
    (recipe
    -0.07
    Variable
    -0.07
    _Collections
    -0.07
    +w
    -0.06
    uple
    -0.06
    nému
    -0.06
     poco
    -0.06
    باشد
    -0.06
    imbledon
    -0.06
    POSITIVE LOGITS
     tvrd
    0.07
     Atomic
    0.07
     Gr
    0.07
    野
    0.06
     세계
    0.06
     platforms
    0.06
     formatDate
    0.06
    bur
    0.06
    Ordinal
    0.06
     ред
    0.06
    Act Density 0.027%

    No Known Activations