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

    Neuronpedia

    INDEX
    Explanations

    Gr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     b
    -0.07
     자신
    -0.06
    几个
    -0.06
     rb
    -0.06
     os
    -0.06
     순간
    -0.06
     Vir
    -0.06
    Contrib
    -0.06
    nah
    -0.06
     Carnegie
    -0.06
    POSITIVE LOGITS
    .handleClick
    0.08
     arrival
    0.07
    +-+-+-+-
    0.07
    uesta
    0.06
     цій
    0.06
     cca
    0.06
    Firstname
    0.06
     arity
    0.06
     náměstí
    0.06
     zeměděl
    0.06
    Act Density 0.006%

    No Known Activations