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

    Neuronpedia

    INDEX
    Explanations

    (E) and (Z) isomers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens—especially floating-point numbers (e.g. measurements, coefficients, or energies) embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nicole
    -0.07
     ringing
    -0.07
     struck
    -0.07
     Bullet
    -0.07
    =$_
    -0.07
    loop
    -0.06
    <TextView
    -0.06
    _half
    -0.06
    (camera
    -0.06
     окрем
    -0.06
    POSITIVE LOGITS
     ترجمه
    0.07
    _-
    0.06
     Valid
    0.06
     بسته
    0.06
    _make
    0.06
    _devices
    0.06
     Vys
    0.06
     sooner
    0.06
    إ
    0.05
    Mp
    0.05
    Act Density 0.008%

    No Known Activations