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

    Neuronpedia

    INDEX
    Explanations

    references to network protocols or system libraries

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

    scheme / plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fun
    -0.45
     aph
    -0.38
     entry
    -0.38
    userAgent
    -0.38
     Ves
    -0.37
    不起
    -0.37
    krebs
    -0.36
    knex
    -0.35
     is
    -0.35
     
    -0.35
    POSITIVE LOGITS
     مخطط
    2.73
     SCHEME
    0.79
     계획
    0.78
    Autoritní
    0.75
    SCHEME
    0.73
     Pläne
    0.71
     فريبيس
    0.70
    cheme
    0.69
    Scheme
    0.69
    adaptiveStyles
    0.67
    Act Density 0.000%

    No Known Activations