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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .empty
    -0.07
    ões
    -0.07
    uction
    -0.07
    處
    -0.06
     perpetrator
    -0.06
    _probs
    -0.06
    'clock
    -0.06
     convergence
    -0.06
     Instrument
    -0.06
     Intent
    -0.06
    POSITIVE LOGITS
     بسبب
    0.07
     jlong
    0.07
     Arizona
    0.07
     anyways
    0.06
    ubi
    0.06
    Facing
    0.06
    ub
    0.06
    Team
    0.06
    ')}}">↵
    0.06
    这个
    0.06
    Act Density 0.035%

    No Known Activations