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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prospective
    -0.08
    ocoder
    -0.08
     saucepan
    -0.08
     Potion
    -0.07
    ాన్ని
    -0.07
     catalyst
    -0.07
    221
    -0.07
    మ
    -0.07
    -dem
    -0.07
    _profit
    -0.07
    POSITIVE LOGITS
     FIG
    0.08
     TAP
    0.08
     Specification
    0.07
    .subscription
    0.07
     Ehren
    0.07
     freiwill
    0.07
     trots
    0.07
     крыш
    0.07
     경
    0.07
     تفاصيل
    0.07
    Act Density 0.000%

    No Known Activations