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

    Neuronpedia

    INDEX
    Explanations

    give me a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    program
    0.41
    to
    0.41
    Provenance
    0.39
    at
    0.39
    Artist
    0.38
    customer
    0.38
    ErrorInfo
    0.38
    Master
    0.37
     Started
    0.37
    notice
    0.36
    POSITIVE LOGITS
    };
    0.41
     desej
    0.37
     émissions
    0.36
     proporcion
    0.35
     towering
    0.35
    },
    0.34
    ické
    0.34
    ера
    0.34
     tween
    0.34
    }.
    0.33
    Act Density 0.009%

    No Known Activations