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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens showing fractional values (floating-point numbers), as found in version strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _SURFACE
    -0.08
    Beyond
    -0.06
    겠습니다
    -0.06
    WithEmailAndPassword
    -0.06
    viz
    -0.06
     otherButtonTitles
    -0.06
    主义
    -0.06
    _noise
    -0.06
    _above
    -0.06
     Vương
    -0.06
    POSITIVE LOGITS
     mixin
    0.06
     aggregation
    0.06
     Dön
    0.06
     Nec
    0.06
     ان
    0.06
    .Manager
    0.06
     analsex
    0.06
     �
    0.06
    یف
    0.06
     yans
    0.06
    Act Density 0.001%

    No Known Activations