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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("/")↵
    -0.07
    าล
    -0.07
    emet
    -0.06
     fabs
    -0.06
    ArgumentException
    -0.06
     Sat
    -0.06
     rolls
    -0.06
     Tot
    -0.06
     tray
    -0.06
    \a
    -0.06
    POSITIVE LOGITS
     alles
    0.07
     strict
    0.06
     프로
    0.06
     struggling
    0.06
    양
    0.06
    _cc
    0.06
     시행
    0.06
    (optimizer
    0.06
     düzen
    0.06
    、今
    0.06
    Act Density 0.041%

    No Known Activations