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

    Neuronpedia

    INDEX
    Explanations

    the word "which" to identify clauses or phrases initiating further explanations or specifications

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

    Mathematical expressions or notation

    np_acts-logits-general · gemini-2.0-flash

    which begins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.61
    wiſe
    -0.59
     ſte
    -0.56
     ब्रेकडाउन
    -0.56
     Efq
    -0.56
     pleaſure
    -0.56
    AddTagHelper
    -0.56
     myſelf
    -0.56
    WriteBarrier
    -0.55
    InputBorder
    -0.53
    POSITIVE LOGITS
    partements
    0.39
     Rückseite
    0.38
     oreja
    0.38
    ➌
    0.35
    bió
    0.34
    '
    0.34
     dudas
    0.34
     visitantes
    0.33
     maceta
    0.33
     lleva
    0.33
    Act Density 0.583%

    No Known Activations