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

    Neuronpedia

    INDEX
    Explanations

    mentions of "units" in various contexts

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

    units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]=='
    -0.54
    >
    -0.49
    retudo
    -0.47
    '=>'
    -0.47
    ]!='
    -0.46
    ]='
    -0.46
    ]=="
    -0.45
    󠁮
    -0.45
     Kerr
    -0.42
     Перейти
    -0.42
    POSITIVE LOGITS
     units
    2.05
     Units
    1.96
    units
    1.91
    Units
    1.90
     unit
    1.69
     UNITS
    1.66
    unit
    1.58
    Unit
    1.49
     Unit
    1.47
    UNITS
    1.44
    Act Density 0.017%

    No Known Activations