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

    Neuronpedia

    INDEX
    Explanations

    Russian and reflexes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ram
    -0.09
     �
    -0.09
    Ram
    -0.08
     wording
    -0.08
     peste
    -0.08
     زر
    -0.08
    انيا
    -0.08
     loom
    -0.08
     bowl
    -0.07
     Mari
    -0.07
    POSITIVE LOGITS
     discretionary
    0.07
     Resist
    0.07
    ummy
    0.07
    measure
    0.07
    unknown
    0.07
     encamin
    0.07
    tır
    0.07
    kol
    0.07
    loe
    0.07
    limit
    0.07
    Act Density 0.002%

    No Known Activations