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

    Neuronpedia

    INDEX
    Explanations

    programming elements related to conditional checks and assignments

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

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.64
    niająca
    -0.50
    DeleteBehavior
    -0.42
    limited
    -0.42
    experienced
    -0.41
    VED
    -0.41
    kháu
    -0.40
    快速
    -0.40
    LIMITED
    -0.40
    illustrated
    -0.38
    POSITIVE LOGITS
     myſelf
    0.55
     itſelf
    0.54
    aarrggbb
    0.49
     snippetHide
    0.49
    endphp
    0.48
     poffible
    0.48
    fromCharCode
    0.47
     pleaſure
    0.47
     consultato
    0.47
    CopyWith
    0.46
    Act Density 0.027%

    No Known Activations