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

    Neuronpedia

    INDEX
    Explanations

    opt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spiral
    -0.07
    $date
    -0.06
    .tooltip
    -0.06
     setError
    -0.06
    Е
    -0.06
    *>(
    -0.06
     Eli
    -0.06
    이야
    -0.06
     rychle
    -0.06
     learner
    -0.06
    POSITIVE LOGITS
    尔
    0.07
     Checks
    0.07
    .Submit
    0.07
     opportun
    0.07
     deserted
    0.07
    'aff
    0.07
     суп
    0.06
     inconsistencies
    0.06
    爾
    0.06
     Talking
    0.06
    Act Density 0.002%

    No Known Activations