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

    Neuronpedia

    INDEX
    Explanations

    expressions of enthusiasm or excitement related to seasonal fashion trends

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

    Follows punctuation (, .)

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by "Plus", "Pair", or "Bonus"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Erfolge
    -0.58
    toFloat
    -0.57
    ,:);
    -0.55
    مراجع
    -0.55
    InstanceState
    -0.55
    underscore
    -0.53
    ſelf
    -0.52
    (".")
    -0.52
     Accordingly
    -0.52
    ('.')
    -0.52
    POSITIVE LOGITS
     Plus
    1.00
     Pair
    0.95
     Bonus
    0.94
    Plus
    0.92
     trust
    0.92
     Grab
    0.91
    Bonus
    0.89
     Who
    0.88
    Grab
    0.88
    Pair
    0.86
    Act Density 0.120%

    No Known Activations