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

    Neuronpedia

    INDEX
    Explanations

    disturbing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maxim
    -0.07
     RegexOptions
    -0.06
     Par
    -0.06
     Qed
    -0.06
    โก
    -0.06
    čný
    -0.06
    azy
    -0.06
    менш
    -0.06
     Enable
    -0.06
     contenu
    -0.06
    POSITIVE LOGITS
     bad
    0.07
    シャ
    0.07
    uba
    0.06
    _subtitle
    0.06
    едак
    0.06
    Inactive
    0.06
     proh
    0.06
     depicting
    0.06
    Sending
    0.06
     widespread
    0.06
    Act Density 0.068%

    No Known Activations