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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical values or statistics in scientific contexts

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

    Appears before a number

    np_acts-logits-general · gemini-2.0-flash

    journal citations with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Бахар
    -0.65
     <=",
    -0.63
    Thunk
    -0.62
    หวัด
    -0.61
    __*/
    -0.54
    __(/*!
    -0.53
    ftagPool
    -0.49
     <<<<<<<<<<<<<<
    -0.49
    DataURL
    -0.47
    éf
    -0.47
    POSITIVE LOGITS
    cerol
    0.53
     désolés
    0.52
    igeon
    0.52
     necks
    0.51
     Ause
    0.49
    wahati
    0.48
    ionato
    0.48
    siveness
    0.48
    borderTop
    0.48
    TextBoxColumn
    0.47
    Act Density 0.172%

    No Known Activations