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

    Neuronpedia

    INDEX
    Explanations

    criminal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attainment
    -0.07
     Adapt
    -0.07
    Black
    -0.07
    	unset
    -0.07
     dialogs
    -0.06
     Gentle
    -0.06
    .middleware
    -0.06
    IO
    -0.06
    lod
    -0.06
    水
    -0.06
    POSITIVE LOGITS
     �
    0.07
     pitched
    0.07
    classify
    0.07
    .getUrl
    0.06
     -↵↵
    0.06
    Existing
    0.06
     шаг
    0.06
    CHANT
    0.06
    vič
    0.06
    ']];↵
    0.06
    Act Density 0.023%

    No Known Activations