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

    Neuronpedia

    INDEX
    Explanations

    decoder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .interval
    -0.07
     ​​
    -0.06
     "+"
    -0.06
     Maul
    -0.06
    uiltin
    -0.06
    /navigation
    -0.06
     brut
    -0.06
     psychiat
    -0.06
    _matrices
    -0.06
     прик
    -0.06
    POSITIVE LOGITS
    ticket
    0.07
     deciding
    0.07
    conc
    0.07
     υ
    0.06
     besch
    0.06
     decoder
    0.06
     consider
    0.06
    _nama
    0.06
    ій
    0.06
    ामक
    0.06
    Act Density 0.002%

    No Known Activations