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

    Neuronpedia

    INDEX
    Explanations

    instances where something operates smoothly or effectively

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

    "[something] works [adverb]"

    np_acts-logits-general · gemini-2.0-flash

    just works fine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISupport
    -0.78
     Eſ
    -0.73
     ſtate
    -0.73
     leaſt
    -0.72
    Geplaatst
    -0.71
     myſelf
    -0.71
     fubject
    -0.65
    GEBURTS
    -0.65
     themſelves
    -0.65
     purpoſe
    -0.64
    POSITIVE LOGITS
     dandy
    0.92
     fine
    0.88
     great
    0.75
     beaut
    0.74
     grand
    0.71
     swell
    0.69
     lovely
    0.66
     charm
    0.64
     sweet
    0.62
    great
    0.61
    Act Density 0.163%

    No Known Activations