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

    Neuronpedia

    INDEX
    Explanations

    Code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    v
    -0.06
    oves
    -0.06
     FAT
    -0.06
    headers
    -0.06
     thoại
    -0.06
    uniacid
    -0.06
    DDS
    -0.06
    �
    -0.06
    BOVE
    -0.06
     Và
    -0.06
    POSITIVE LOGITS
     emot
    0.07
    ANCED
    0.06
     interim
    0.06
    	new
    0.06
     statues
    0.06
     lubric
    0.06
     consumers
    0.06
     feather
    0.06
     acting
    0.06
     excursion
    0.06
    Act Density 0.000%

    No Known Activations