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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terminology and references in research or academic contexts

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

    regarding a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    glTexCoord
    -0.33
    UnusedPrivate
    -0.31
     medalla
    -0.31
     amistad
    -0.30
     kred
    -0.30
     nargin
    -0.29
    醒了
    -0.29
     akade
    -0.29
    拍了
    -0.28
    렀
    -0.28
    POSITIVE LOGITS
     оригіналу
    0.57
     BoxFit
    0.56
     mxArray
    0.53
    Cyfeiriadau
    0.53
    лтемелер
    0.51
    İstinadlar
    0.51
    ləş
    0.50
    hyrchwyd
    0.50
    sing
    0.49
     relève
    0.49
    Act Density 0.618%

    No Known Activations