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

    Neuronpedia

    INDEX
    Explanations

    breakdown and mechanism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     İstanbul
    0.48
    Cape
    0.46
    पेड
    0.46
     Ankara
    0.46
     biosolids
    0.45
     ANYTHING
    0.45
     Cape
    0.44
    जाम
    0.44
    Türk
    0.44
     Erit
    0.44
    POSITIVE LOGITS
    radioButton
    0.38
    ->
    0.38
    Knight
    0.37
    loggedIn
    0.37
    rom
    0.36
    chan
    0.36
    *}
    0.36
    QtGui
    0.36
    sten
    0.36
    tie
    0.35
    Act Density 0.000%

    No Known Activations