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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to layers and angles

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

    arrangement and timing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.68
    ToProps
    -0.49
    PullParser
    -0.48
    Abp
    -0.48
    MIDDLEWARE
    -0.46
    Spoljašnje
    -0.46
    vání
    -0.45
    DispatchToProps
    -0.44
    rália
    -0.44
    >>>>>>>
    -0.43
    POSITIVE LOGITS
     numbered
    0.73
     angled
    0.72
    Layered
    0.70
     ranked
    0.69
    layered
    0.68
     styled
    0.68
     Ranked
    0.68
     lined
    0.68
     tiered
    0.68
    timed
    0.67
    Act Density 0.037%

    No Known Activations