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

    Neuronpedia

    INDEX
    Explanations

    vision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MPs
    -0.08
     oldValue
    -0.08
    (edges
    -0.08
    ⋼
    -0.07
     помог
    -0.07
     aún
    -0.07
    ока
    -0.07
    Heavy
    -0.07
    Spawn
    -0.07
    umont
    -0.07
    POSITIVE LOGITS
     Armor
    0.07
    规则
    0.07
    NSUInteger
    0.07
     authorized
    0.06
     shit
    0.06
     marital
    0.06
    italize
    0.06
     AN
    0.06
    0.06
    anger
    0.06
    Act Density 0.003%

    No Known Activations