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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating functions and benefits in various contexts

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

    provides benefits or functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     David
    -0.40
    David
    -0.33
     politics
    -0.33
     Herzen
    -0.33
     Politics
    -0.32
     America
    -0.32
    ited
    -0.32
    johtaja
    -0.32
     China
    -0.32
     politique
    -0.31
    POSITIVE LOGITS
     kasarigan
    0.83
    tagHelperRunner
    0.71
     onOptions
    0.68
     MainAxisSize
    0.68
    expandindo
    0.67
    httphttps
    0.66
    IntoConstraints
    0.65
    OGND
    0.65
    出版年
    0.63
     surla
    0.63
    Act Density 0.029%

    No Known Activations