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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цей
    -0.07
     Train
    -0.07
     belts
    -0.06
     省
    -0.06
     ''),
    -0.06
    stinence
    -0.06
     Bapt
    -0.06
     ents
    -0.06
    UnitOfWork
    -0.06
     JsonConvert
    -0.05
    POSITIVE LOGITS
     signup
    0.07
    sav
    0.07
    VALUE
    0.07
    Tambah
    0.07
    iveau
    0.07
    Ơ
    0.07
    uido
    0.07
    -Control
    0.06
    _shell
    0.06
     Goblin
    0.06
    Act Density 0.000%

    No Known Activations