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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shortly
    -0.08
    Miller
    -0.07
     اللبن
    -0.06
     Strict
    -0.06
     Seconds
    -0.06
     struggled
    -0.06
     Smoking
    -0.06
    墨
    -0.06
     серии
    -0.06
     כאילו
    -0.06
    POSITIVE LOGITS
     לחוק
    0.07
    >|
    0.07
    _field
    0.07
     Comey
    0.07
     compareTo
    0.07
    흔
    0.07
    _CRYPTO
    0.07
    (one
    0.07
    encryption
    0.07
    .kotlin
    0.06
    Act Density 0.013%

    No Known Activations