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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    말
    -0.07
    	mv
    -0.07
    .util
    -0.07
    }-${
    -0.07
     soda
    -0.06
     Appendix
    -0.06
     вла
    -0.06
     Example
    -0.06
     conclusive
    -0.06
     responseBody
    -0.06
    POSITIVE LOGITS
     it
    0.08
     It
    0.08
    -it
    0.07
    brit
    0.07
    ,it
    0.07
    winner
    0.07
    _Label
    0.06
    VertexAttribArray
    0.06
    —it
    0.06
    els
    0.06
    Act Density 0.026%

    No Known Activations