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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TG
    -0.07
    前世
    -0.07
    А
    -0.07
    🤭
    -0.07
     EVT
    -0.07
     conceivable
    -0.07
     CX
    -0.07
    下巴
    -0.06
     orgas
    -0.06
     Tax
    -0.06
    POSITIVE LOGITS
    (sa
    0.07
     members
    0.07
    ומים
    0.07
     bottles
    0.07
     usable
    0.07
     onde
    0.06
     musicians
    0.06
    (Editor
    0.06
    rites
    0.06
     Quaternion
    0.06
    Act Density 0.001%

    No Known Activations