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

    Neuronpedia

    INDEX
    Explanations

    occurrences of closing braces and parentheses in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    -0.68
     psicológica
    -0.45
    følgelig
    -0.43
    örté
    -0.43
     braccia
    -0.43
    UnusedPrivate
    -0.41
     싶
    -0.41
    CC
    -0.41
    CL
    -0.41
     Eriksen
    -0.41
    POSITIVE LOGITS
    }+
    1.14
    }-
    1.02
    }}+
    0.91
    }}-
    0.78
    )}+
    0.73
     }}-
    0.69
    }+(
    0.69
    }+\
    0.68
    )}-
    0.68
    }}},
    0.68
    Act Density 0.021%

    No Known Activations