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

    Neuronpedia

    INDEX
    Explanations

    statistical comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bit
    -0.07
     persuasion
    -0.07
    ウ
    -0.07
    路
    -0.07
     Petite
    -0.07
     Ly
    -0.07
     adv
    -0.07
    New
    -0.06
    (server
    -0.06
    Vis
    -0.06
    POSITIVE LOGITS
    =null
    0.07
    的权利
    0.07
    gae
    0.07
    ñas
    0.07
    �
    0.07
    rabbit
    0.07
     NOTE
    0.07
    촛
    0.07
     blacks
    0.07
    _RGCTX
    0.06
    Act Density 0.023%

    No Known Activations