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

    Neuronpedia

    INDEX
    Explanations

    matrix entries & coefficients

    np_max-act · gemini-2.0-flash

    This neuron fires on references to the numerical details or parameters of matrices in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    $total
    -0.06
    VIS
    -0.06
    .SE
    -0.06
    ocale
    -0.06
    _Register
    -0.06
    anced
    -0.06
     stranded
    -0.06
    olen
    -0.06
     foll
    -0.06
    >r
    -0.06
    POSITIVE LOGITS
     Mak
    0.07
     Pick
    0.06
     завд
    0.06
     obtained
    0.06
     Pic
    0.06
    ?”
    0.06
    (Column
    0.06
     explore
    0.06
    -item
    0.06
    _Camera
    0.06
    Act Density 0.023%

    No Known Activations