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

    Neuronpedia

    INDEX
    Explanations

    sentences with punctuation and phrasing related to conditional and hypothetical scenarios

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

    Follows periods or non-english text

    np_acts-logits-general · gemini-2.0-flash

    lists and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unrecognized
    -0.53
     ziren
    -0.49
     Paus
    -0.49
    OneToMany
    -0.49
    かわらず
    -0.46
    着用
    -0.46
    UpInside
    -0.45
     nguyễn
    -0.44
    ing
    -0.43
     Hecht
    -0.43
    POSITIVE LOGITS
     autorytatywna
    1.21
     AssemblyTitle
    0.82
    abestanden
    0.81
    Personensuche
    0.80
    IsMutable
    0.79
    Aiheesta
    0.74
    verwijspagina
    0.68
     Meanwhile
    0.68
    قایناق‌لار
    0.67
    FunctionFlags
    0.67
    Act Density 0.047%

    No Known Activations