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

    Neuronpedia

    INDEX
    Explanations

    python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "}
    0.94
    ?}
    0.83
    '}
    0.78
    .}
    0.75
    ?\\
    0.75
    ("%
    0.74
     }=
    0.74
    Polynomial
    0.74
    """
    0.73
    }=-
    0.72
    POSITIVE LOGITS
    баев
    0.82
     clippings
    0.71
     Plea
    0.71
    จับ
    0.70
     Reformed
    0.68
    換え
    0.67
     getUsersBy
    0.66
     Stellung
    0.66
     روی
    0.66
     paci
    0.66
    Act Density 0.099%

    No Known Activations