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

    Neuronpedia

    INDEX
    Explanations

    terms related to reputation and performance metrics

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

    Following "track", "criminal", "safety" or "prior"

    np_acts-logits-general · gemini-2.0-flash

    track record and reputation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.73
    кульп
    -0.66
    complexContent
    -0.65
    AsUp
    -0.63
     jLabel
    -0.61
    })->
    -0.61
    WebServlet
    -0.61
    tiéndose
    -0.59
     arşivlendi
    -0.59
    swire
    -0.59
    POSITIVE LOGITS
     record
    2.34
     track
    2.33
    record
    1.95
    track
    1.86
     Record
    1.82
     Track
    1.80
     RECORD
    1.77
    Record
    1.74
    Track
    1.69
     history
    1.67
    Act Density 0.241%

    No Known Activations