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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens representing decimal or floating-point values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Aly
    -0.06
    ;t
    -0.06
     parents
    -0.06
    Allows
    -0.06
     erased
    -0.06
    丈
    -0.06
    yn
    -0.06
    Canon
    -0.06
     Julie
    -0.06
     App
    -0.06
    POSITIVE LOGITS
    ümü
    0.07
    (SS
    0.07
    ého
    0.07
     PublicKey
    0.07
    랜드
    0.07
    _ot
    0.06
     :",
    0.06
     tirelessly
    0.06
    _inst
    0.06
    =\"%
    0.06
    Act Density 0.194%

    No Known Activations