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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buffers
    -0.07
     FIFO
    -0.06
     hash
    -0.06
    ’.↵↵
    -0.06
     由
    -0.06
     Panel
    -0.06
    (hw
    -0.06
     Media
    -0.06
     Hash
    -0.06
     ""),↵
    -0.06
    POSITIVE LOGITS
    firstName
    0.07
     lick
    0.07
    .Stage
    0.07
    .PIPE
    0.07
    挑
    0.07
     Buen
    0.07
    	assert
    0.07
    :ss
    0.07
     bell
    0.07
    =torch
    0.07
    Act Density 0.044%

    No Known Activations