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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     queen
    -0.07
     outputs
    -0.06
     Chang
    -0.06
     Stranger
    -0.06
    말
    -0.06
    backward
    -0.06
     světě
    -0.06
    �
    -0.06
     американ
    -0.06
     Nadu
    -0.06
    POSITIVE LOGITS
    055
    0.07
    .Euler
    0.06
    etCode
    0.06
    ("//*[@
    0.06
    085
    0.06
    NEXT
    0.06
    .Exception
    0.06
     habitual
    0.06
    086
    0.06
     graduation
    0.06
    Act Density 0.003%

    No Known Activations