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

    Neuronpedia

    INDEX
    Explanations

    filtering, debugging, and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …………………………………………
    1.04
    0.96
    0.91
    0.90
                                   
    0.89
    0.86
    0.78
    0.78
    することができます
    0.78
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.77
    POSITIVE LOGITS
     др
    0.88
     Govt
    0.85
     soln
    0.83
     amus
    0.78
     alat
    0.77
     ppl
    0.76
     guia
    0.73
    /...
    0.73
     gov
    0.73
    ..,
    0.70
    Act Density 0.194%

    No Known Activations