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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe complex systems or structures

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

    describing complex scientific phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pne
    -0.46
     پن
    -0.36
     lượt
    -0.36
    ДД
    -0.36
     palladium
    -0.35
     lapar
    -0.35
     ✭✭
    -0.35
    Portable
    -0.34
    BP
    -0.34
    principalColumn
    -0.34
    POSITIVE LOGITS
     ExecuteAsync
    0.71
     compleja
    0.70
     compless
    0.67
     complex
    0.66
     '\\;'
    0.64
     complexe
    0.57
    writeFieldEnd
    0.56
     complexo
    0.56
     esponja
    0.56
     complejo
    0.56
    Act Density 0.032%

    No Known Activations