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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عشق
    -0.07
     lòng
    -0.06
     mw
    -0.06
    UU
    -0.06
     نیر
    -0.06
    тик
    -0.06
    pow
    -0.06
     Ihr
    -0.06
     Broadway
    -0.06
     Zi
    -0.06
    POSITIVE LOGITS
    .registry
    0.07
     entitled
    0.07
     Andre
    0.07
     pozem
    0.07
     Cyprus
    0.07
    .lastName
    0.06
    .Te
    0.06
    .setAlignment
    0.06
    usions
    0.06
    +'_
    0.06
    Act Density 0.028%

    No Known Activations