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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and regression modeling

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

    influence function and tails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kebijakan
    -0.35
    ükemmel
    -0.35
    Autoritní
    -0.35
     Italijani
    -0.34
     Centuries
    -0.34
     flotte
    -0.33
     melainkan
    -0.33
     CreateTagHelper
    -0.33
     typelib
    -0.32
    assemblée
    -0.32
    POSITIVE LOGITS
    DockStyle
    0.66
    MLLoader
    0.59
    TagMode
    0.53
     الرياضيه
    0.52
     BoxFit
    0.51
    nloa
    0.50
    mybatisplus
    0.50
     outliers
    0.49
     outlier
    0.49
    \{\\
    0.49
    Act Density 0.408%

    No Known Activations