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

    Neuronpedia

    INDEX
    Explanations

    terms related to sharpness or clarity

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

    "sharp"

    np_acts-logits-general · gemini-2.0-flash

    sharp bounds, gradients, criticism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fluence
    -0.67
    limus
    -0.65
    RegistryLite
    -0.63
    ...)
    -0.62
    ...")
    -0.62
    ...",
    -0.61
     ...
    -0.61
    …
    -0.60
    ldots
    -0.59
    ...</
    -0.59
    POSITIVE LOGITS
     Sharp
    1.21
     sharp
    1.15
     SHARP
    1.07
    sharp
    1.04
    Sharp
    0.94
     Shar
    0.91
     sharpness
    0.86
     sharpen
    0.86
     sharper
    0.86
     SHAR
    0.84
    Act Density 0.144%

    No Known Activations