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

    Neuronpedia

    INDEX
    Explanations

    special characters or formatting tags in the text

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

    text, code, json, dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.48
     bParam
    -0.43
    enterOuterAlt
    -0.42
     hosp
    -0.41
     referrerpolicy
    -0.41
    DetailComponent
    -0.39
    Fprintf
    -0.39
    vVar
    -0.38
     soal
    -0.37
    LayoutStyle
    -0.37
    POSITIVE LOGITS
    StoryboardSegue
    0.60
     estekak
    0.49
    Cyfeiriadau
    0.48
     مشين
    0.46
     OnTriggerEnter
    0.44
     препратки
    0.41
     ویکی‌پدیای
    0.41
    jets
    0.40
     infierno
    0.40
     
    0.39
    Act Density 0.003%

    No Known Activations