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

    Neuronpedia

    INDEX
    Explanations

    specific numerical patterns or formats, particularly those related to codes and identifiers

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

    words ending in f

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ust
    -0.50
     بيها
    -0.43
    elett
    -0.41
     Escribe
    -0.40
    ierz
    -0.38
    cher
    -0.37
    aires
    -0.37
    ios
    -0.37
    inst
    -0.37
     debió
    -0.37
    POSITIVE LOGITS
     ujednoznacz
    0.74
    expandindo
    0.60
     myſelf
    0.57
     itſelf
    0.56
    Tembelea
    0.54
    \{\\
    0.52
     himſelf
    0.51
     Administrativna
    0.50
    windowFixed
    0.50
    adaptiveStyles
    0.49
    Act Density 0.121%

    No Known Activations