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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ѫ
    -0.07
    тся
    -0.07
    зв
    -0.07
    amphetamine
    -0.07
    DialogTitle
    -0.07
     people
    -0.07
     ridiculous
    -0.07
    ятия
    -0.07
     Cham
    -0.07
     При
    -0.07
    POSITIVE LOGITS
     WIN
    0.07
    OPER
    0.07
     autonomy
    0.07
    Days
    0.07
    .LOC
    0.07
     seg
    0.06
     SYNC
    0.06
     Wellness
    0.06
     العالي
    0.06
    Parent
    0.06
    Act Density 0.070%

    No Known Activations