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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    既然
    -0.06
     heroine
    -0.06
    fore
    -0.06
    相
    -0.06
    takes
    -0.06
     Wei
    -0.06
    \t
    -0.06
     Truly
    -0.06
     dagen
    -0.05
     orbit
    -0.05
    POSITIVE LOGITS
    �
    0.08
     Πα
    0.07
    Override
    0.06
    couz
    0.06
    ,A
    0.06
    ังกล
    0.06
    아서
    0.06
     mirrors
    0.06
    EDA
    0.06
    )localObject
    0.06
    Act Density 0.013%

    No Known Activations