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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     automated
    -0.07
    нак
    -0.07
    وند
    -0.07
     machines
    -0.07
    なら
    -0.07
    /video
    -0.06
    бина
    -0.06
    .WebControls
    -0.06
    	loop
    -0.06
    matching
    -0.06
    POSITIVE LOGITS
     conj
    0.07
    /internal
    0.06
    endif
    0.06
     четвер
    0.06
    指定
    0.06
    instant
    0.06
    .productId
    0.06
    Executable
    0.06
     déf
    0.06
    ",-
    0.06
    Act Density 0.065%

    No Known Activations