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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuestros
    -0.07
    ul
    -0.07
    Supplier
    -0.07
    )");
↵
    -0.06
    #
    -0.06
    ?
↵
    -0.06
    or
    -0.06
    Mas
    -0.06
    IMIT
    -0.06
     χω
    -0.06
    POSITIVE LOGITS
     Belgian
    0.07
     Chiến
    0.07
    acific
    0.07
     resmi
    0.06
    udy
    0.06
     قانون
    0.06
     vibr
    0.06
    .:.:.:.
    0.06
    ibraries
    0.06
     cardi
    0.06
    Act Density 0.001%

    No Known Activations