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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expire
    -0.08
     sine
    -0.08
    clamp
    -0.07
    Università
    -0.07
     ith
    -0.07
    总
    -0.07
    íf
    -0.07
     tg
    -0.07
    سمي
    -0.07
    *num
    -0.07
    POSITIVE LOGITS
    ﭷ
    0.07
     PAC
    0.07
     Replica
    0.07
     wrapping
    0.06
     installations
    0.06
     assembly
    0.06
     항상
    0.06
    .Fl
    0.06
    /column
    0.06
     enclosure
    0.06
    Act Density 0.001%

    No Known Activations