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

    Neuronpedia

    INDEX
    Explanations

    starting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esus
    -0.07
     surge
    -0.07
     spree
    -0.06
     allows
    -0.06
    وتر
    -0.06
    енка
    -0.06
     looming
    -0.06
     code
    -0.06
    І
    -0.06
     Sailor
    -0.06
    POSITIVE LOGITS
     Pasadena
    0.08
     COVER
    0.07
     disgusting
    0.07
    _(
    0.06
     ú
    0.06
     peasant
    0.06
     Hole
    0.06
    族自治
    0.06
     таких
    0.06
     digestive
    0.06
    Act Density 0.169%

    No Known Activations