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

    Neuronpedia

    INDEX
    Explanations

    sql

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    208
    -0.07
     Era
    -0.07
    八
    -0.07
    ubishi
    -0.07
     produced
    -0.07
     concentrate
    -0.07
    268
    -0.07
    'h
    -0.06
    coop
    -0.06
    pectrum
    -0.06
    POSITIVE LOGITS
     SQL
    0.07
     Gospel
    0.07
    SI
    0.06
    /sql
    0.06
    SSF
    0.06
     Esk
    0.06
     答
    0.06
     CSRF
    0.06
    _sql
    0.06
     Israel
    0.06
    Act Density 0.013%

    No Known Activations