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

    Neuronpedia

    INDEX
    Explanations

    inverse

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    )new
    -0.07
     Mang
    -0.07
     osoby
    -0.06
     تیم
    -0.06
    retched
    -0.06
    Rooms
    -0.06
     Coff
    -0.06
     lem
    -0.06
    _IF
    -0.06
     bad
    -0.06
    POSITIVE LOGITS
     newValue
    0.07
    [parent
    0.07
     первый
    0.07
     Jacqueline
    0.06
    イク
    0.06
     Uploaded
    0.06
     ✔
    0.06
    νου
    0.06
     ا�
    0.06
     διά
    0.06
    Act Density 0.000%

    No Known Activations