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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    a numeric token (numbers and numeric-looking tokens, including decimals).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    회사
    -0.07
    	with
    -0.06
    üstü
    -0.06
    contra
    -0.06
    	os
    -0.06
     commercials
    -0.06
     Corporation
    -0.06
    .''↵↵
    -0.06
    arde
    -0.06
     thẩm
    -0.06
    POSITIVE LOGITS
    BYTES
    0.07
     влия
    0.07
    мель
    0.06
     Cald
    0.06
     titre
    0.06
     Samp
    0.06
    omit
    0.06
    arov
    0.06
     marché
    0.06
    订
    0.06
    Act Density 2.856%

    No Known Activations