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

    Neuronpedia

    INDEX
    Explanations

    Opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dit
    -0.07
     Rotate
    -0.07
    価格
    -0.06
     Heads
    -0.06
     microsoft
    -0.06
     ridiculously
    -0.06
    submission
    -0.06
    quito
    -0.06
    eeee
    -0.06
     Lumpur
    -0.06
    POSITIVE LOGITS
    ivalence
    0.06
     빌
    0.06
     proportional
    0.06
     пой
    0.06
     toxic
    0.06
    sz
    0.06
    ifying
    0.06
     tofu
    0.06
    व
    0.06
    dbg
    0.06
    Act Density 0.079%

    No Known Activations