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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or evaluations

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

    "value"

    np_acts-logits-general · gemini-2.0-flash

    value of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.49
     Mur
    -0.37
     General
    -0.37
     Second
    -0.37
    *******
    -0.37
    [[
    -0.35
     sol
    -0.35
    General
    -0.35
     ph
    -0.35
     Sol
    -0.34
    POSITIVE LOGITS
     ModelExpression
    0.66
    ReusableCell
    0.60
     getValue
    0.60
    IsMutable
    0.59
     Value
    0.59
     kasarigan
    0.59
     ​​
    0.57
     समीक्षाओं
    0.56
     proposition
    0.52
     Valer
    0.51
    Act Density 0.231%

    No Known Activations