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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or inquiry

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

    Follows non-English words/characters

    np_acts-logits-general · gemini-2.0-flash

    technical descriptions and factual statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.46
     utafitiHapana
    -0.46
    rungsseite
    -0.43
     saites
    -0.43
    complexContent
    -0.42
    ğını
    -0.41
     faſt
    -0.41
    -0.41
    様です
    -0.41
     poffe
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    0.65
    UrlResolution
    0.50
    这款
    0.43
    underlying
    0.42
    endphp
    0.42
     виправивши
    0.42
    newtheorem
    0.41
     InputDecoration
    0.40
    ódó
    0.40
     autorytatywna
    0.40
    Act Density 0.022%

    No Known Activations