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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that refer to things being disrupted or broken

    oai_token-act-pair · gemini-2.0-flash

    break

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     break
    -3.13
     Break
    -3.05
     breaking
    -2.97
    break
    -2.95
    Break
    -2.94
     breaks
    -2.94
     broken
    -2.91
     broke
    -2.86
     BREAK
    -2.78
     Breaks
    -2.73
    POSITIVE LOGITS
    awtextra
    0.54
     ganda
    0.46
    ]]);
    0.46
    󠁢
    0.45
     acepción
    0.42
    OptionsMenu
    0.42
     (*.
    0.41
    OTS
    0.41
    atterns
    0.41
    цы
    0.41
    Act Density 1.954%

    No Known Activations