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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scheme
    -0.07
     grave
    -0.06
    "So
    -0.06
    .isBlank
    -0.06
    _hover
    -0.06
    egrity
    -0.06
    かし
    -0.06
    regunta
    -0.06
    n
    -0.06
    _assert
    -0.06
    POSITIVE LOGITS
    _logic
    0.07
    (delta
    0.07
    실
    0.07
     Zag
    0.07
     німець
    0.06
    __/
    0.06
    	wc
    0.06
    /Y
    0.06
     eles
    0.06
     пром
    0.06
    Act Density 0.017%

    No Known Activations