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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    place
    -0.07
    umu
    -0.06
     CHANNEL
    -0.06
    -details
    -0.06
    ully
    -0.06
     typ
    -0.06
     Password
    -0.06
    ponential
    -0.06
     bureauc
    -0.06
     университ
    -0.06
    POSITIVE LOGITS
    щини
    0.08
     Goth
    0.06
    _MAIN
    0.06
             
    0.06
    _St
    0.06
     وی
    0.06
    _rect
    0.06
     subsidiary
    0.06
    ainting
    0.06
     autre
    0.06
    Act Density 0.011%

    No Known Activations