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

    Neuronpedia

    INDEX
    Explanations

    what is going on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -cols
    -0.09
    ìĽħ
    -0.09
    ebek
    -0.09
    .bs
    -0.08
     Aires
    -0.08
    cps
    -0.08
    datable
    -0.08
     ðŁĺī\n\n
    -0.08
    iore
    -0.08
     Tome
    -0.08
    POSITIVE LOGITS
     behind
    0.11
     between
    0.09
    /how
    0.09
     Hick
    0.09
    enda
    0.09
    ÅĽcie
    0.09
     happened
    0.09
    emon
    0.09
     canv
    0.08
     Qin
    0.08
    Act Density 0.041%

    No Known Activations