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

    Neuronpedia

    INDEX
    Explanations

    improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    281
    -0.07
     }↵↵↵↵↵
    -0.06
    Initialization
    -0.06
    bial
    -0.06
    QUIT
    -0.06
    LIN
    -0.06
    한다
    -0.06
    lical
    -0.06
     Threads
    -0.06
    ificant
    -0.06
    POSITIVE LOGITS
    lookup
    0.07
    掌
    0.07
    :"",
    0.06
    (Output
    0.06
     tailor
    0.06
    _usec
    0.06
     하고
    0.06
     düzen
    0.06
     commemorate
    0.06
     arasındaki
    0.06
    Act Density 0.045%

    No Known Activations