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

    Neuronpedia

    INDEX
    Explanations

    different types of classifications or categorizations

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

    "of" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    type of classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Previews
    -0.77
    GraphicsUnit
    -0.68
     démission
    -0.65
     Normdatei
    -0.63
    MLLoader
    -0.63
     disponibilità
    -0.62
    ViewFeatures
    -0.62
     volontà
    -0.62
     colère
    -0.60
     atât
    -0.60
    POSITIVE LOGITS
    uesday
    0.71
     material
    0.69
     thing
    0.68
    )':
    0.65
     behavior
    0.62
    _=
    0.61
    "");
    0.61
    型的
    0.61
    "',
    0.59
    okes
    0.59
    Act Density 0.189%

    No Known Activations