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

    Neuronpedia

    INDEX
    Explanations

    fix formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     principals
    0.39
     resear
    0.38
    ణు
    0.36
     suffers
    0.36
     hitters
    0.36
    чному
    0.35
     crews
    0.35
    rared
    0.35
    mprj
    0.35
    чом
    0.35
    POSITIVE LOGITS
    $.)
    0.43
     Lösung
    0.42
     Oktober
    0.42
     thấy
    0.40
     solución
    0.40
     Herb
    0.40
     hê
    0.40
    Herb
    0.39
     اکتوبر
    0.39
     İç
    0.39
    Act Density 0.000%

    No Known Activations