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

    Neuronpedia

    INDEX
    Explanations

    complex data structures and identifiers

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

    Hexadecimal-like sequences

    np_acts-logits-general · gemini-2.0-flash

    custom IDs like 00NJ00000022gx0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.85
     оригіналу
    -0.73
     >=",
    -0.72
     تانيه
    -0.69
    InjectAttribute
    -0.65
    новништво
    -0.65
    "}";
    -0.64
    ]")]
    -0.61
     famí
    -0.60
    脚注の使い方
    -0.59
    POSITIVE LOGITS
     Legendre
    0.48
     deal
    0.48
     $[-
    0.48
     Juda
    0.46
    Composable
    0.46
     Reverso
    0.46
    dańsk
    0.45
    umenten
    0.45
     Czechoslovakia
    0.44
     EDTA
    0.44
    Act Density 0.128%

    No Known Activations