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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     су
    -0.08
     stormed
    -0.07
    гран
    -0.07
    فو
    -0.07
    érience
    -0.07
    .progress
    -0.07
     Fusion
    -0.07
     Fortune
    -0.06
    _middle
    -0.06
    Charge
    -0.06
    POSITIVE LOGITS
    חברתי
    0.07
    凄
    0.06
     sister
    0.06
    til
    0.06
    (lst
    0.06
    äch
    0.06
    epochs
    0.06
    ↱
    0.06
    北京市
    0.06
     snippet
    0.06
    Act Density 0.005%

    No Known Activations