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

    Neuronpedia

    INDEX
    Explanations

    US state abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kron
    -0.07
    xis
    -0.07
    โน
    -0.07
     kus
    -0.07
     Hollow
    -0.07
     ";
    -0.07
     Asset
    -0.07
    graph
    -0.06
     mechanical
    -0.06
     Sys
    -0.06
    POSITIVE LOGITS
    黎
    0.07
     韓
    0.07
    awaii
    0.06
    quiries
    0.06
    C
    0.06
     (:
    0.06
    .password
    0.06
     vál
    0.06
     NSW
    0.06
     greatly
    0.06
    Act Density 0.015%

    No Known Activations