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

    Neuronpedia

    INDEX
    Explanations

    queries related to selecting and retrieving datasets or objects

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

    "all" followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    all followed by a set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.97
     مشين
    -0.74
    WriteTagHelper
    -0.72
    SequentialGroup
    -0.72
    !*\
    -0.61
    breos
    -0.61
    ItemBackground
    -0.60
    __':
    -0.59
    MigrationBuilder
    -0.58
    StoreMessageInfo
    -0.58
    POSITIVE LOGITS
     available
    0.86
     eligible
    0.81
     possible
    0.78
     all
    0.74
    符合
    0.73
     potential
    0.72
     relevant
    0.71
    available
    0.70
     known
    0.70
     registered
    0.68
    Act Density 0.731%

    No Known Activations