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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating possibility, desire, or necessity

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

    possibility or hypothetical situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.71
    ArrowToggle
    -0.63
     Infórmanos
    -0.63
    fjspx
    -0.60
     Efq
    -0.57
    styleType
    -0.55
    OGND
    -0.55
    tagext
    -0.52
     informée
    -0.52
    MERCIAL
    -0.52
    POSITIVE LOGITS
     might
    0.82
     may
    0.74
    might
    0.66
    อาจ
    0.62
     Might
    0.61
    Might
    0.60
     kanskje
    0.58
     MIGHT
    0.56
     möglicherweise
    0.56
    かもしれません
    0.56
    Act Density 0.830%

    No Known Activations