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

    Neuronpedia

    INDEX
    Explanations

    Java method calls and variable manipulations in programming code

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.70
    GGLE
    -0.55
    */),
    -0.52
    Jîn
    -0.52
     <=",
    -0.51
    ',
    -0.50
    Dữ
    -0.49
     ***!
    -0.49
     Bartolo
    -0.48
    praš
    -0.48
    POSITIVE LOGITS
    PerformLayout
    0.60
    roek
    0.60
    :
    0.59
     invokingState
    0.58
    omitempty
    0.54
     CreateTagHelper
    0.53
    .)
    0.53
    .'
    0.52
    .
    0.51
    ."
    0.50
    Act Density 0.068%

    No Known Activations