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

    Neuronpedia

    INDEX
    Explanations

    expressions related to guidance and supportive interactions

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

    positive contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.63
    tableFuture
    -0.53
    MLLoader
    -0.53
    rungsseite
    -0.51
    #+#
    -0.50
    typeorm
    -0.49
     vectorielles
    -0.47
     gráficos
    -0.46
     abstrato
    -0.46
     mecánico
    -0.46
    POSITIVE LOGITS
    новниш
    0.46
    ivin
    0.41
    nach
    0.41
     تضيفلها
    0.38
    aper
    0.38
    VAR
    0.38
    win
    0.37
    earned
    0.37
    ende
    0.37
     Haar
    0.37
    Act Density 0.023%

    No Known Activations