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

    Neuronpedia

    INDEX
    Explanations

    summary and general notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     begint
    0.28
    ပ်
    0.28
    ᅳ
    0.28
    വിധ
    0.27
     incontinence
    0.27
     vésicules
    0.27
     defies
    0.26
     analges
    0.26
     streamwise
    0.26
     সুতরাং
    0.25
    POSITIVE LOGITS
    概要
    0.32
    kowe
    0.27
    般的
    0.27
    "]}
    0.26
    摘要
    0.26
    })-
    0.25
     --
    0.25
    orphan
    0.25
     dor
    0.25
    "--
    0.25
    Act Density 0.004%

    No Known Activations