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

    Neuronpedia

    INDEX
    Explanations

    rest

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens beginning with the root “rest” (e.g. “Rest,” “Resting,” “Restoration,” “Restenosis”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Muhammad
    -0.08
     Kumar
    -0.08
    FileName
    -0.07
     camera
    -0.07
     امیر
    -0.07
     Mayer
    -0.07
    .generate
    -0.07
     azimuth
    -0.07
     Gaussian
    -0.07
     cuda
    -0.07
    POSITIVE LOGITS
     rest
    0.16
     Rest
    0.13
    st
    0.11
    rest
    0.10
    Rest
    0.10
    ст
    0.10
     rested
    0.10
     REST
    0.09
    .rest
    0.09
    ста
    0.08
    Act Density 0.016%

    No Known Activations