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

    Neuronpedia

    INDEX
    Explanations

    structured references and citation formats within the text

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

    citation markers `[@...]`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pracovní
    -0.41
    SequentialGroup
    -0.36
    attente
    -0.35
    ulus
    -0.35
     gustar
    -0.34
     udrž
    -0.33
    ienen
    -0.32
     line
    -0.31
    Descubre
    -0.31
     ligt
    -0.31
    POSITIVE LOGITS
     Houſe
    0.69
     houſe
    0.67
     ſta
    0.66
     purpoſe
    0.65
     kasarigan
    0.65
     myſelf
    0.59
    ſelf
    0.59
     Monfieur
    0.59
     raiſ
    0.59
     Inſ
    0.57
    Act Density 0.264%

    No Known Activations