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

    Neuronpedia

    INDEX
    Explanations

    special characters and specific formatting elements in text

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

    Text after "and" or "&"

    np_acts-logits-general · gemini-2.0-flash

    list separators and subsequent items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.69
    ist
    -0.55
     же
    -0.53
     regres
    -0.51
    دانشنامهٔ
    -0.51
    الإنجليزية
    -0.51
    RTLD
    -0.50
    ValueStyle
    -0.49
    초
    -0.49
    Hauptartikel
    -0.48
    POSITIVE LOGITS
    ﹠
    0.71
    andafter
    0.63
     \&
    0.63
     ostavi
    0.60
    amp
    0.58
    \&
    0.56
     $\&$
    0.56
    othesis
    0.55
    EnableWeb
    0.54
    PROLOG
    0.54
    Act Density 0.156%

    No Known Activations