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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    のご
    0.38
    iens
    0.36
     "¿
    0.36
     企业
    0.35
    鍑
    0.35
    ómo
    0.35
    ेंडर
    0.35
    iums
    0.35
    ユニット
    0.35
    टेगरी
    0.35
    POSITIVE LOGITS
    //
    0.37
    ****
    0.36
    netlify
    0.35
    +"\
    0.34
    decorate
    0.34
    akti
    0.33
    [...]
    0.33
    mapStateToProps
    0.33
    •
    0.33
    add
    0.33
    Act Density 0.007%

    No Known Activations