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

    Neuronpedia

    INDEX
    Explanations

    calculate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )),
↵
    -0.06
    !")
↵
    -0.06
     암
    -0.06
    (percent
    -0.06
     стара
    -0.06
     Apps
    -0.06
    -suite
    -0.06
    '])){
↵
    -0.06
    	raw
    -0.06
    ))),↵
    -0.06
    POSITIVE LOGITS
     bikes
    0.07
    Price
    0.07
    blk
    0.07
    _Block
    0.07
     bribery
    0.07
     duck
    0.07
     hopes
    0.07
    hh
    0.06
     falsehood
    0.06
    noun
    0.06
    Act Density 0.000%

    No Known Activations