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

    Neuronpedia

    INDEX
    Explanations

    special characters and mathematical symbols

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

    different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.84
    ंदीखरीदारी
    -0.73
    parsedMessage
    -0.70
     GenerationType
    -0.67
     referrerpolicy
    -0.66
     CreateTagHelper
    -0.66
     Infórmanos
    -0.65
     صوتيه
    -0.65
    ftagPool
    -0.64
    AccessorTable
    -0.57
    POSITIVE LOGITS
     ohnehin
    0.43
     아니라
    0.40
     maquin
    0.37
     sowieso
    0.37
     Reihe
    0.37
     boyunca
    0.37
     gorro
    0.36
     capuche
    0.36
     almohada
    0.35
    multirow
    0.34
    Act Density 0.016%

    No Known Activations