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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deep
    -0.07
     swearing
    -0.07
    kus
    -0.06
    ому
    -0.06
    ść
    -0.06
     wann
    -0.06
     cliff
    -0.06
     punches
    -0.06
    κά
    -0.06
    .ol
    -0.06
    POSITIVE LOGITS
     Lowest
    0.07
    .productId
    0.06
    _dependencies
    0.06
     multid
    0.06
     textSize
    0.06
     \<^
    0.06
     Gast
    0.05
     respected
    0.05
     componentDidMount
    0.05
     perder
    0.05
    Act Density 0.005%

    No Known Activations