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

    Neuronpedia

    INDEX
    Explanations

    Quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ClassName
    -0.07
     Naturally
    -0.07
    ावन
    -0.06
     infancy
    -0.06
    Driver
    -0.06
    GenerationStrategy
    -0.06
    sc
    -0.06
    StackSize
    -0.06
     startPos
    -0.06
     hips
    -0.06
    POSITIVE LOGITS
    _learn
    0.07
     enable
    0.07
    μέ
    0.06
    يير
    0.06
    rina
    0.06
    quests
    0.06
    09
    0.06
    _stop
    0.06
     test
    0.06
     allev
    0.06
    Act Density 0.015%

    No Known Activations