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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and punctuation marks in the text

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

    words, textLabel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.58
    SequentialGroup
    -0.53
     ſte
    -0.52
    tvguidetime
    -0.52
    bootstrapcdn
    -0.51
     صوتيه
    -0.50
    styleType
    -0.49
    Становништво
    -0.49
    ftagPool
    -0.48
    StoryboardSegue
    -0.48
    POSITIVE LOGITS
     words
    0.35
    ########.
    0.34
    ima
    0.34
    words
    0.32
    ̲
    0.31
    ql
    0.31
    Ree
    0.31
    eckel
    0.30
    textLabel
    0.30
    rie
    0.30
    Act Density 0.985%

    No Known Activations