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

    Neuronpedia

    INDEX
    Explanations

    the character 'v' representing various contexts or terms related to vectors

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

    Questions, math, or code snippets

    np_acts-logits-general · gemini-2.0-flash

    HSV ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.75
    tanleria
    -0.70
     pinulongan
    -0.64
    MERCIAL
    -0.62
     BRARY
    -0.61
    inghouse
    -0.59
    giphy
    -0.57
    leſs
    -0.57
    astéroïdes
    -0.57
    VERTISEMENT
    -0.56
    POSITIVE LOGITS
    j
    0.66
    J
    0.65
    .'
    0.61
    ).'
    0.59
    I
    0.59
    ':
    0.58
     quelcon
    0.57
     specialmente
    0.57
     honra
    0.56
     sobretudo
    0.55
    Act Density 0.182%

    No Known Activations