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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ех
    -0.07
    _ENT
    -0.07
     deserves
    -0.07
    solver
    -0.06
     деятель
    -0.06
     getLast
    -0.06
    epoch
    -0.06
    官方
    -0.06
    stackpath
    -0.06
     Warm
    -0.06
    POSITIVE LOGITS
     babel
    0.08
    �
    0.07
     Clearly
    0.07
     █
    0.06
     hoàn
    0.06
     rag
    0.06
    Graphics
    0.06
     tensorflow
    0.06
    juan
    0.06
    vre
    0.06
    Act Density 0.001%

    No Known Activations