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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron responds to single‐letter generic type parameters (like “E”, “F”, or “T”) in type declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     clf
    -0.07
    류
    -0.07
     unusual
    -0.07
    เหล
    -0.06
     noteworthy
    -0.06
     Vue
    -0.06
    xiv
    -0.06
     VAL
    -0.06
     rough
    -0.06
     Tourism
    -0.06
    POSITIVE LOGITS
    ripsi
    0.07
     reuse
    0.06
     […]↵↵
    0.06
    يلة
    0.06
    ільки
    0.06
    něm
    0.06
    inks
    0.06
    ponsive
    0.06
    '};↵
    0.06
     み
    0.06
    Act Density 0.109%

    No Known Activations