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

    Neuronpedia

    INDEX
    Explanations

    (T

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    富
    -0.07
     พ
    -0.07
    �
    -0.06
    planes
    -0.06
    нять
    -0.06
    _Part
    -0.06
    uzz
    -0.06
    "He
    -0.06
     kesinlikle
    -0.06
    、三
    -0.06
    POSITIVE LOGITS
    _predictions
    0.07
     renew
    0.07
     자동
    0.07
     forthcoming
    0.07
     Pont
    0.06
     strapon
    0.06
    _caption
    0.06
     Jaguar
    0.06
    _t
    0.06
     latter
    0.06
    Act Density 0.001%

    No Known Activations