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

    Neuronpedia

    INDEX
    Explanations

    concepts related to doubt and complexity in life and society

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

    Text after ellipsis or continuation markers

    np_acts-logits-general · gemini-2.0-flash

    seepage dripping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientras
    -0.56
     Besuch
    -0.53
     increí
    -0.52
     colgantes
    -0.48
     garrafa
    -0.48
    ambién
    -0.48
     femei
    -0.48
     geladeira
    -0.47
     keduanya
    -0.46
     chapéu
    -0.46
    POSITIVE LOGITS
    цездатний
    0.59
     Италијани
    0.51
     فريبيس
    0.49
    ThroughAttribute
    0.46
     Савезне
    0.45
    TagMode
    0.45
     ویکی‌پدی
    0.45
    IntoConstraints
    0.44
    $}}
    0.42
    :✨
    0.42
    Act Density 1.037%

    No Known Activations