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

    Neuronpedia

    INDEX
    Explanations

    items related to probability and statistical estimators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LR moment, estimator, kernel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.63
     Préférences
    -0.52
    Angelo
    -0.51
     Benedetto
    -0.49
     Bunting
    -0.49
    …
    -0.49
     donat
    -0.48
    Santo
    -0.47
    subplots
    -0.47
    IsMutable
    -0.47
    POSITIVE LOGITS
     LR
    2.09
    LR
    2.08
    lr
    1.80
     lr
    1.66
    Lr
    1.26
    lrr
    0.81
     NLR
    0.73
     LRT
    0.72
    lru
    0.69
     SLR
    0.67
    Act Density 0.010%

    No Known Activations