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

    Neuronpedia

    INDEX
    Explanations

    structured data formats and their attributes

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

    technical identifiers and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.75
     Савезне
    -0.75
    GEBURTS
    -0.71
    دانشنامهٔ
    -0.66
    WriteTagHelper
    -0.66
    ########.
    -0.63
     Biôgrafia
    -0.61
     Roskov
    -0.59
    parsedMessage
    -0.59
     Signalez
    -0.57
    POSITIVE LOGITS
     lượt
    0.42
     necessarily
    0.41
     lastly
    0.41
     now
    0.41
     respectively
    0.40
    cora
    0.40
     <<<<<<<<<<<<<<
    0.40
     nữa
    0.40
    hall
    0.40
    Fontes
    0.39
    Act Density 0.016%

    No Known Activations