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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and common sentence structures

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

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.98
     يتيمه
    -0.84
    tvguidetime
    -0.71
    Datuak
    -0.71
    CloseOperation
    -0.70
     surla
    -0.69
    ViewInit
    -0.67
    setVerticalGroup
    -0.66
    évaluateur
    -0.65
    transQ
    -0.64
    POSITIVE LOGITS
     Stoffe
    0.41
     sauve
    0.37
     intérieure
    0.37
    Composição
    0.37
    arrière
    0.36
     serez
    0.36
     froide
    0.34
     Schwerpunkt
    0.34
     Gallardo
    0.34
     opdracht
    0.33
    Act Density 0.011%

    No Known Activations