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

    Neuronpedia

    INDEX
    Explanations

    creation/building

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    下去
    -0.07
     única
    -0.07
     Unidos
    -0.07
     invested
    -0.06
     reve
    -0.06
     샤
    -0.06
    Root
    -0.06
     yeter
    -0.06
    하며
    -0.06
     ORDER
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .conv
    0.06
    CEPTION
    0.06
    rod
    0.06
    [i
    0.06
    (Un
    0.06
     AFP
    0.06
    	thread
    0.06
    ']):↵
    0.06
    chy
    0.06
    Act Density 0.044%

    No Known Activations