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

    Neuronpedia

    INDEX
    Explanations

    expressions of potential or possibility in the context of decision-making

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

    possibility and speculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nodoc
    -0.51
    ThemeOverlay
    -0.43
    visuel
    -0.42
     skall
    -0.40
     sienta
    -0.40
     continuó
    -0.39
     VIDEOTAPE
    -0.38
    Бахар
    -0.38
    并将
    -0.38
    cektir
    -0.37
    POSITIVE LOGITS
    Might
    0.92
     Might
    0.85
    might
    0.84
     might
    0.84
     MIGHT
    0.69
     könnte
    0.63
    getMinutes
    0.59
     ought
    0.55
    Somebody
    0.55
     somebody
    0.54
    Act Density 0.036%

    No Known Activations