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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "unique" and related terms indicating distinctiveness

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

    "unique" or its variations

    np_acts-logits-general · gemini-2.0-flash

    unique storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utilisons
    -0.61
    olella
    -0.54
     cser
    -0.54
    pherds
    -0.53
    ynnwys
    -0.49
     هيا
    -0.49
     portugués
    -0.49
     Scrolls
    -0.49
     Universitaria
    -0.49
    图源
    -0.48
    POSITIVE LOGITS
     UNIQUE
    0.85
     uniqu
    0.80
    Unique
    0.80
    UNIQUE
    0.79
     Unique
    0.78
    unique
    0.77
    principalTable
    0.75
     uniques
    0.74
    windowFixed
    0.73
    átní
    0.72
    Act Density 0.080%

    No Known Activations