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

    Neuronpedia

    INDEX
    Explanations

    belt

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “belt.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Indiana
    -0.07
    Destroy
    -0.07
     consumers
    -0.07
     Christmas
    -0.07
     اینجا
    -0.07
    486
    -0.07
    _indx
    -0.07
     Pixar
    -0.07
    iana
    -0.06
     Cyan
    -0.06
    POSITIVE LOGITS
     belt
    0.13
     Belt
    0.12
     belts
    0.10
    belt
    0.09
    eln
    0.08
    elt
    0.07
    負
    0.07
    带
    0.07
     llev
    0.07
     Bolt
    0.07
    Act Density 0.006%

    No Known Activations