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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ичної
    -0.06
     boilers
    -0.06
    イド
    -0.06
     transport
    -0.06
     discharge
    -0.06
    anse
    -0.06
     CP
    -0.06
     Doc
    -0.06
    Friends
    -0.06
    Rgb
    -0.06
    POSITIVE LOGITS
    ?</
    0.07
    	rc
    0.07
     bát
    0.07
     Justice
    0.06
    ulet
    0.06
     saint
    0.06
    ‚
    0.06
    -await
    0.06
     وه
    0.06
    ?>
↵
    0.06
    Act Density 0.036%

    No Known Activations