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

    Neuronpedia

    INDEX
    Explanations

    applied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Page
    -0.08
     göz
    -0.06
    iry
    -0.06
    _ls
    -0.06
     другим
    -0.06
    368
    -0.06
     таб
    -0.06
    usa
    -0.06
    (flags
    -0.06
    (argv
    -0.06
    POSITIVE LOGITS
    INESS
    0.07
     messed
    0.07
     hưởng
    0.07
    supplier
    0.07
    _OPERATOR
    0.07
    )size
    0.07
     dried
    0.06
     classics
    0.06
    .reactivex
    0.06
    多い
    0.06
    Act Density 0.027%

    No Known Activations