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

    Neuronpedia

    INDEX
    Explanations

    objects and their properties in programming contexts

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

    Code-related tokens and symbols

    np_acts-logits-general · gemini-2.0-flash

    object and variable assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ())).
    -0.61
    rungsseite
    -0.61
    Chham
    -0.61
    ()?;
    -0.60
     plus
    -0.58
     and
    -0.58
    ())))
    -0.56
     Sélectionnez
    -0.56
    )))),
    -0.55
    '}),
    -0.55
    POSITIVE LOGITS
    IntoConstraints
    0.75
    ImageContext
    0.69
    soever
    0.64
     APE
    0.61
    DockStyle
    0.60
    zae
    0.59
     lagerfeld
    0.57
     GIPHY
    0.56
     endregion
    0.56
     leaſt
    0.55
    Act Density 0.209%

    No Known Activations