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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‌ترین
    -0.08
    (connection
    -0.07
    шку
    -0.06
    ITY
    -0.06
    erence
    -0.06
    .IsAny
    -0.06
    Construct
    -0.06
    Its
    -0.06
    lid
    -0.06
    Furthermore
    -0.06
    POSITIVE LOGITS
    quoise
    0.08
     Crowley
    0.07
     Fresno
    0.07
     broad
    0.07
     EURO
    0.06
    _DO
    0.06
     neb
    0.06
     disgust
    0.06
     cooler
    0.06
    بیر
    0.06
    Act Density 0.115%

    No Known Activations