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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mac
    -0.06
    deps
    -0.06
    258
    -0.06
    Σ
    -0.06
    uids
    -0.06
     районе
    -0.06
    REW
    -0.06
    _coef
    -0.06
    974
    -0.06
    (ver
    -0.06
    POSITIVE LOGITS
    Messenger
    0.07
     trump
    0.07
    젝트
    0.06
     Charlotte
    0.06
     Dummy
    0.06
     much
    0.06
    message
    0.06
     Intelligence
    0.06
     Tristan
    0.06
    Архівовано
    0.06
    Act Density 0.018%

    No Known Activations