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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΄
    -0.07
     '%'
    -0.06
     greatest
    -0.06
     serge
    -0.06
     recession
    -0.06
    -0.06
    	y
    -0.06
     acclaimed
    -0.06
    atı
    -0.06
     TableRow
    -0.06
    POSITIVE LOGITS
    _TESTS
    0.07
     gets
    0.07
     politik
    0.07
    UTERS
    0.06
     durumu
    0.06
     rz
    0.06
    _processes
    0.06
     NOI
    0.06
    可是
    0.06
    pt
    0.06
    Act Density 0.005%

    No Known Activations