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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     designation
    -0.07
     Woods
    -0.07
    dur
    -0.07
    frog
    -0.06
    	of
    -0.06
    anda
    -0.06
     الأح
    -0.06
     organis
    -0.06
    Rightarrow
    -0.06
    ันทร
    -0.06
    POSITIVE LOGITS
     not
    0.07
     мил
    0.07
    .WARNING
    0.07
     REPLACE
    0.06
    .notification
    0.06
    /****************************************************************************↵
    0.06
     мик
    0.06
     ऋ
    0.06
    vid
    0.06
     to
    0.06
    Act Density 0.003%

    No Known Activations