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

    Neuronpedia

    INDEX
    Explanations

    evidence and relationships in scientific research data

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

    Statements, conclusions, or results

    np_acts-logits-general · gemini-2.0-flash

    academic findings and conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.78
    XMLSchema
    -0.60
     équip
    -0.54
     GenerationType
    -0.54
     Rè
    -0.52
     préférences
    -0.51
    setopt
    -0.50
     nakalista
    -0.49
     réduction
    -0.49
     rè
    -0.48
    POSITIVE LOGITS
     draw
    0.62
     shed
    0.59
     concluded
    0.58
    Panamoan
    0.57
     illustrated
    0.57
     pointed
    0.56
     clarified
    0.55
    shed
    0.55
     conclude
    0.55
    PerformLayout
    0.54
    Act Density 0.769%

    No Known Activations