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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating skepticism or doubt

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

    Text after a conjunction

    np_acts-logits-general · gemini-2.0-flash

    specific technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.47
     оригіналу
    -0.47
    هن
    -0.41
    hows
    -0.39
     saluto
    -0.38
    annia
    -0.38
     admir
    -0.36
    withIdentifier
    -0.36
    fycat
    -0.36
    StatusOK
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    0.67
    tvguidetime
    0.63
    StoryboardSegue
    0.59
    Derbyniad
    0.58
     հղումներ
    0.56
     OFDb
    0.56
    MessageTagHelper
    0.52
     cherchés
    0.50
     invokingState
    0.50
    なんと
    0.48
    Act Density 0.500%

    No Known Activations