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

    Neuronpedia

    INDEX
    Explanations

    code tokens

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literal tokens—especially floating-point numbers embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LoginPage
    -0.07
    BufferData
    -0.06
     VG
    -0.06
    狠
    -0.06
    (Y
    -0.06
    руч
    -0.06
    دى
    -0.06
     Ranger
    -0.06
     CPI
    -0.06
    venting
    -0.06
    POSITIVE LOGITS
    _bins
    0.06
     zem
    0.06
     �
    0.06
     Lomb
    0.06
     ymax
    0.06
     pretrained
    0.06
     simp
    0.06
     bạn
    0.06
    تیب
    0.06
    criminal
    0.06
    Act Density 0.013%

    No Known Activations