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

    Neuronpedia

    INDEX
    Explanations

    physics simulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    れば
    -0.07
    нувся
    -0.07
    活
    -0.07
    ndef
    -0.07
    кон
    -0.07
    requency
    -0.07
    н
    -0.07
     anth
    -0.07
    quad
    -0.07
    (req
    -0.07
    POSITIVE LOGITS
     toto
    0.07
    	flash
    0.06
     Rogers
    0.06
    _cs
    0.06
     `,↵
    0.06
    ags
    0.06
     financier
    0.06
    meal
    0.06
     Addison
    0.06
    ';
↵
    0.06
    Act Density 0.012%

    No Known Activations