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
     لأن
    -0.07
     wed
    -0.07
    xdd
    -0.06
    (bl
    -0.06
    .deleted
    -0.06
     зменш
    -0.06
    에는
    -0.06
    kę
    -0.06
     wannonce
    -0.06
    Compare
    -0.06
    POSITIVE LOGITS
    ioni
    0.07
    inha
    0.07
    bh
    0.07
    едера
    0.07
    [E
    0.07
    ILA
    0.06
     Mess
    0.06
    _TIMES
    0.06
    iffer
    0.06
    ATS
    0.06
    Act Density 0.007%

    No Known Activations