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

    Neuronpedia

    INDEX
    Explanations

    repetitive expressions of "nothing" or related terms

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

    nothing followed by else, more, or happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ganu
    -0.48
     evt
    -0.47
    Trie
    -0.46
    PDT
    -0.45
    setStroke
    -0.45
    CONSIN
    -0.44
    idated
    -0.44
    Pyx
    -0.43
     transfieras
    -0.43
     lựa
    -0.43
    POSITIVE LOGITS
     nothing
    1.12
     Nothing
    1.09
    nothing
    1.07
     NOTHING
    1.06
    Nothing
    1.03
    NOTHING
    1.00
     nothin
    0.90
     Nada
    0.81
    Nichts
    0.78
     anything
    0.77
    Act Density 0.010%

    No Known Activations