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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mer
    -0.08
    .mar
    -0.07
    _EVENTS
    -0.07
    .depart
    -0.07
     NSDictionary
    -0.07
     Wir
    -0.07
    hexdigest
    -0.07
    SError
    -0.06
    .DATA
    -0.06
    /version
    -0.06
    POSITIVE LOGITS
     Layer
    0.07
     roaring
    0.07
     шир
    0.06
     bulky
    0.06
     liked
    0.06
    “你
    0.06
     Weak
    0.06
     Plain
    0.06
     unfortunate
    0.06
     мови
    0.06
    Act Density 0.001%

    No Known Activations