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

    Neuronpedia

    INDEX
    Explanations

    descriptions of problem-solving methods or strategies

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

    fix or solve problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.79
    Autoritní
    -0.61
     houſe
    -0.60
     pleaſure
    -0.59
     utafitiHapana
    -0.56
     itſelf
    -0.56
     estekak
    -0.56
     faſt
    -0.54
     ſta
    -0.53
    ckså
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.46
     Improved
    0.42
     improved
    0.41
     overcome
    0.37
    ftagPool
    0.36
    Sole
    0.36
     impact
    0.35
     solve
    0.35
     AP
    0.34
     increased
    0.34
    Act Density 0.133%

    No Known Activations