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

    Neuronpedia

    INDEX
    Explanations

    Flint-related contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asses
    -0.08
    Wake
    -0.08
     occup
    -0.08
    ghest
    -0.07
    leave
    -0.07
    ハード
    -0.07
     Mess
    -0.07
    RAIN
    -0.07
     fuels
    -0.07
    Week
    -0.07
    POSITIVE LOGITS
    (Color
    0.08
    alchemy
    0.07
    (tf
    0.07
    ington
    0.07
    .compile
    0.06
    公
    0.06
    _utf
    0.06
    (bl
    0.06
    ываем
    0.06
    銷
    0.06
    Act Density 0.001%

    No Known Activations