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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or structures, particularly arrays or matrices, in a document

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

    Math mode arrays/matrices

    np_acts-logits-general · gemini-2.0-flash

    array formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.53
    !
    -0.53
    rrggbb
    -0.53
     nahilalakip
    -0.52
     !$
    -0.49
    lanzen
    -0.49
    藹
    -0.47
    !,
    -0.47
    $
    -0.47
    !)
    -0.47
    POSITIVE LOGITS
     الرياضيه
    0.64
    /></
    0.61
    enumii
    0.59
     empf
    0.55
    новништво
    0.55
    GEBURTSDATUM
    0.51
    łop
    0.50
    schra
    0.50
    NUMX
    0.48
    ThemeOverlay
    0.48
    Act Density 0.117%

    No Known Activations