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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    408
    -0.07
     remaining
    -0.06
    (field
    -0.06
    ropical
    -0.06
    Providers
    -0.06
    _fx
    -0.06
    mux
    -0.06
    [file
    -0.06
    ();
↵
↵
    -0.06
    hos
    -0.06
    POSITIVE LOGITS
    ’util
    0.07
    IsRequired
    0.06
    "":
    0.06
     almost
    0.06
     동
    0.06
    .every
    0.06
     Оп
    0.06
     色
    0.06
     choisir
    0.06
     Ген
    0.06
    Act Density 0.018%

    No Known Activations