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

    Neuronpedia

    INDEX
    Explanations

    technical details regarding experiments and methods

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

    Tokens within parentheses

    np_acts-logits-general · gemini-2.0-flash

    pieces of body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.54
    MessageOf
    -0.53
    WithIOException
    -0.52
    LookAnd
    -0.51
    disfraz
    -0.51
    Diweddarwch
    -0.47
    AutoScaleMode
    -0.46
    دانشنامهٔ
    -0.45
    Personensuche
    -0.45
    afficheront
    -0.45
    POSITIVE LOGITS
    wapV
    0.40
    chakra
    0.37
    council
    0.37
     provision
    0.37
     council
    0.36
    GIH
    0.35
     motoru
    0.33
     COUNCIL
    0.33
    lamento
    0.33
    Vege
    0.32
    Act Density 1.626%

    No Known Activations