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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity or defined characteristics

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

    clarity, definition, or specificity

    np_acts-logits-general · gemini-2.0-flash

    clearly defined or specific attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.51
     препратки
    -0.46
    SuppressMessage
    -0.40
     NSObject
    -0.39
     negotiations
    -0.38
     Evolution
    -0.38
     ConstraintSet
    -0.35
    POINTER
    -0.35
     Cav
    -0.35
     libération
    -0.35
    POSITIVE LOGITS
    setVerticalGroup
    0.61
     nonUne
    0.53
     sólido
    0.52
     definido
    0.52
    ########.
    0.50
     sólida
    0.50
     fijo
    0.50
     fija
    0.48
     sahibi
    0.48
     definite
    0.47
    Act Density 0.603%

    No Known Activations