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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical representations

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

    ",354" in timestamps

    np_acts-logits-general · gemini-2.0-flash

    timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fourth
    -0.52
    чет
    -0.49
     Four
    -0.48
     fourth
    -0.47
    Fourth
    -0.47
     Ten
    -0.45
     four
    -0.45
    россий
    -0.43
     kit
    -0.43
     Ver
    -0.42
    POSITIVE LOGITS
    Aiheesta
    0.98
    WriteBarrier
    0.94
    OGND
    0.83
    SourceChecksum
    0.79
     виправивши
    0.79
    abestanden
    0.78
     houſe
    0.78
    rawDesc
    0.77
     leaſt
    0.77
     Anſ
    0.76
    Act Density 0.238%

    No Known Activations