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

    Neuronpedia

    INDEX
    Explanations

    forum posts with times/dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expl
    -0.08
     True
    -0.07
    _validator
    -0.07
     constellation
    -0.07
     scarce
    -0.07
    .ops
    -0.07
     podem
    -0.07
     oxidative
    -0.07
     cloned
    -0.07
     dür
    -0.07
    POSITIVE LOGITS
    .chapter
    0.06
    िरफ
    0.06
    ujemy
    0.06
    Eff
    0.06
    Aff
    0.06
     τη
    0.06
     رابط
    0.06
     látky
    0.06
    /testing
    0.06
    .Here
    0.06
    Act Density 0.246%

    No Known Activations