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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谓
    -0.08
     gören
    -0.07
    -new
    -0.07
    하면서
    -0.07
    Mus
    -0.07
    輪
    -0.07
    ciler
    -0.07
     jint
    -0.07
     alternatives
    -0.06
    PYTHON
    -0.06
    POSITIVE LOGITS
     ende
    0.06
     chancellor
    0.05
     protr
    0.05
    demand
    0.05
    andid
    0.05
     guarda
    0.05
     اینچ
    0.05
    riv
    0.05
     bots
    0.05
     koşul
    0.05
    Act Density 0.360%

    No Known Activations