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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on decimal numbers (floating-point values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wine
    -0.07
     Arabs
    -0.06
    rel
    -0.06
    -rel
    -0.06
    DDR
    -0.06
    ensen
    -0.06
    YLON
    -0.06
    HttpContext
    -0.06
     EXEC
    -0.06
     Diabetes
    -0.06
    POSITIVE LOGITS
     enchanted
    0.08
     Robin
    0.07
     LIMITED
    0.07
    dı
    0.07
    .getCode
    0.07
     حضور
    0.06
    тий
    0.06
    dn
    0.06
    oq
    0.06
     foolish
    0.06
    Act Density 0.057%

    No Known Activations