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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships

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

    Likert scales or continuums

    np_acts-logits-general · gemini-2.0-flash

    Likert scale and spectrum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AppModule
    -0.68
    ItemBackground
    -0.64
    adpleegd
    -0.48
    EDEFAULT
    -0.47
    ViewById
    -0.44
    DisplayMode
    -0.43
     Sif
    -0.43
     ProtoMessage
    -0.43
     withal
    -0.43
    outState
    -0.42
    POSITIVE LOGITS
     scale
    1.40
     spectrum
    1.28
     hierarchy
    1.25
     Scale
    1.18
     ladder
    1.12
     escala
    1.11
    scale
    1.11
     scales
    1.07
     SCALE
    1.06
     continuum
    1.05
    Act Density 0.327%

    No Known Activations