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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or preference

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

    my X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.57
    embe
    -0.53
    wegen
    -0.51
     anse
    -0.50
    reste
    -0.49
     AnyObject
    -0.48
     Minden
    -0.47
     Mangel
    -0.47
     سكانية
    -0.46
    angelo
    -0.46
    POSITIVE LOGITS
    Slf
    0.66
    Хьажоргаш
    0.57
    ArgsConstructor
    0.56
    :✨
    0.53
     Nucl
    0.52
    SBATCH
    0.52
    icoot
    0.50
     cappuccio
    0.50
     Wikimedijinoj
    0.48
     IBOutlet
    0.47
    Act Density 0.005%

    No Known Activations