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

    Neuronpedia

    INDEX
    Explanations

    expressions of emphasis or strong feelings

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

    is this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.61
     tranſ
    -0.60
     ویکی‌پدی
    -0.59
     raiſ
    -0.59
     ſch
    -0.58
     ſtre
    -0.57
     Houſe
    -0.57
     تضيفلها
    -0.55
     Reſ
    -0.55
    Xna
    -0.54
    POSITIVE LOGITS
     nonetheless
    0.35
     largely
    0.35
     verlo
    0.34
    permitAll
    0.34
     primarily
    0.34
     TextInputType
    0.33
     nevertheless
    0.32
     fully
    0.32
     precisely
    0.32
     retail
    0.31
    Act Density 0.031%

    No Known Activations