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

    Neuronpedia

    INDEX
    Explanations

    titles, names, locations, groups or other proper nouns

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.63
     He
    -0.58
    bufio
    -0.56
    imageio
    -0.54
    lexikon
    -0.53
     tỏ
    -0.52
    $[
    -0.48
    vatar
    -0.48
     BorderRadius
    -0.47
    anovich
    -0.47
    POSITIVE LOGITS
     myſelf
    0.71
     betweenstory
    0.68
     مشين
    0.65
     Réponses
    0.63
    expandindo
    0.63
    Datuak
    0.61
     Exactos
    0.57
     насељу
    0.56
     हूं
    0.54
     Tinker
    0.54
    Act Density 14.360%

    No Known Activations