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

    Neuronpedia

    INDEX
    Explanations

    facts and trivia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mium
    -0.07
     entrev
    -0.07
    _STENCIL
    -0.07
    들도
    -0.06
    sí
    -0.06
     BUILD
    -0.06
     四
    -0.06
     Back
    -0.06
     regimen
    -0.06
    Dot
    -0.06
    POSITIVE LOGITS
     equilibrium
    0.07
     dept
    0.07
     }()↵
    0.06
     kb
    0.06
     giai
    0.06
    .Dictionary
    0.06
     singapore
    0.06
    Hel
    0.06
    製
    0.06
     ου
    0.06
    Act Density 0.011%

    No Known Activations