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

    Neuronpedia

    INDEX
    Explanations

    complex grammatical constructions, particularly those that express uncertainty or regret

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

    Japanese past-tense verbs and auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    past tense verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.64
    bootstrapcdn
    -0.64
    ArrowToggle
    -0.64
    DeleteBehavior
    -0.64
     Roskov
    -0.63
    Spoljašnje
    -0.61
     
    -0.60
    TypedDataSet
    -0.57
     Shakspeare
    -0.57
    AddTagHelper
    -0.57
    POSITIVE LOGITS
     volo
    0.53
    Indeed
    0.49
     religieuses
    0.47
     précie
    0.46
     Indeed
    0.46
    ädie
    0.45
    /*
    0.45
    tá
    0.45
    sworth
    0.45
    há
    0.44
    Act Density 0.043%

    No Known Activations