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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dense
    -0.07
    -by
    -0.07
    最初
    -0.06
     tamp
    -0.06
    fft
    -0.06
    	bs
    -0.06
    ERV
    -0.06
    .Screen
    -0.06
    Rs
    -0.06
    Kom
    -0.06
    POSITIVE LOGITS
     ara
    0.06
    وزيع
    0.06
     struggle
    0.06
     });↵
    0.06
     Koh
    0.06
     paired
    0.06
     church
    0.06
    .keys
    0.06
    elem
    0.06
     Gib
    0.06
    Act Density 0.059%

    No Known Activations