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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal numbers and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.88
    S
    0.74
    }')
    0.73
     }\
    0.72
    }\
    0.69
     साल
    0.68
     anguish
    0.67
    }&=
    0.64
    strftime
    0.63
    tingham
    0.63
    POSITIVE LOGITS
    的问题
    0.76
    του
    0.69
    น
    0.68
    са
    0.68
    د
    0.66
    сист
    0.66
    </h3>
    0.64
     polít
    0.64
     pręd
    0.63
    νό
    0.63
    Act Density 0.027%

    No Known Activations