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

    Neuronpedia

    INDEX
    Explanations

    blocks of code or programming language syntax

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

    Code-like text or file paths

    np_acts-logits-general · gemini-2.0-flash

    code comments and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.57
     un
    -0.55
     can
    -0.55
     n
    -0.54
     und
    -0.54
     g
    -0.53
     G
    -0.53
     vor
    -0.53
     on
    -0.50
     off
    -0.50
    POSITIVE LOGITS
     Pingback
    0.85
     itſelf
    0.83
     doubtnut
    0.78
     <<<<<<<<<<<<<<
    0.77
    tagHelperRunner
    0.77
     مشين
    0.75
     myſelf
    0.74
     poffible
    0.74
     ſeveral
    0.71
     metav
    0.71
    Act Density 0.068%

    No Known Activations