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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate proposals or suggestions in research contexts

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

    proposed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.40
    Translatef
    -0.35
    cracy
    -0.34
    Portály
    -0.33
    demographic
    -0.33
     dinos
    -0.33
     dinosau
    -0.33
    exams
    -0.33
     Roskov
    -0.33
    
    -0.33
    POSITIVE LOGITS
     proposed
    1.23
    proposed
    1.09
     proposing
    1.05
     propose
    0.98
     suggested
    0.97
     proposé
    0.95
    Proposed
    0.95
     Proposed
    0.93
     proposes
    0.93
     proposée
    0.90
    Act Density 0.049%

    No Known Activations