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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to diversity and uniqueness in experiences or perspectives

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

    Adjectives before nouns

    np_acts-logits-general · gemini-2.0-flash

    adjective describing a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Filmographie
    -0.60
     ArrayAdapter
    -0.59
    PhysRev
    -0.56
    ImageContext
    -0.53
     समीक्षक
    -0.53
     Werden
    -0.52
    ophilia
    -0.51
    isseurs
    -0.51
    lessness
    -0.50
    Одно
    -0.50
    POSITIVE LOGITS
    Välislingid
    0.58
    RetentionPolicy
    0.56
     quantité
    0.53
    AxisAlignment
    0.51
    secuencias
    0.51
    BASEPATH
    0.50
     المعيارى
    0.50
    věř
    0.48
    endal
    0.48
     cantidad
    0.47
    Act Density 0.671%

    No Known Activations