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

    Neuronpedia

    INDEX
    Explanations

    affirmative and definitive statements or terms

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

    Adverbs that modify past participles

    np_acts-logits-general · gemini-2.0-flash

    adverb then verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     émotion
    -0.61
     AssemblyTitle
    -0.58
     marins
    -0.58
     sær
    -0.54
     médicaux
    -0.53
     humaine
    -0.52
     mourut
    -0.52
    Writes
    -0.52
     ferdig
    -0.51
     étoit
    -0.50
    POSITIVE LOGITS
    RegistryLite
    0.89
     be
    0.81
     have
    0.79
    ValueStyle
    0.74
    BufferException
    0.70
    weile
    0.68
     become
    0.65
    enumii
    0.65
     оригіналу
    0.65
    ConstraintMaker
    0.65
    Act Density 0.204%

    No Known Activations