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

    Neuronpedia

    INDEX
    Explanations

    say punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @synthesize
    -0.09
     CLL
    -0.07
     cán
    -0.07
    loe
    -0.07
    atio
    -0.07
     science
    -0.07
    🦁
    -0.06
    .boolean
    -0.06
    ﰞ
    -0.06
    /manage
    -0.06
    POSITIVE LOGITS
     ave
    0.07
     perí
    0.07
    都非常
    0.06
    上百
    0.06
    (Roles
    0.06
     roster
    0.06
     babel
    0.06
     bron
    0.06
    ispers
    0.06
     Bron
    0.06
    Act Density 0.166%

    No Known Activations