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

    Neuronpedia

    INDEX
    Explanations

    mentions of hardware

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

    hardware and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Географиясе
    -0.49
     <<<<<<<<<<<<<<
    -0.46
     Biôgrafia
    -0.46
    Sow
    -0.45
    ExtendWith
    -0.44
    anine
    -0.44
     Lohan
    -0.44
    Brendan
    -0.43
    Geplaatst
    -0.42
    ipedia
    -0.42
    POSITIVE LOGITS
     Hardware
    1.43
     hardware
    1.40
    Hardware
    1.33
    hardware
    1.30
    HARDWARE
    1.08
    硬件
    0.93
     HARD
    0.69
    ハード
    0.63
     HW
    0.60
     hård
    0.59
    Act Density 0.002%

    No Known Activations