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

    Neuronpedia

    INDEX
    Explanations

    code metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raci
    -0.07
    ICES
    -0.07
    чаются
    -0.07
    토
    -0.06
     corridor
    -0.06
     orgy
    -0.06
     DISPATCH
    -0.06
     vegas
    -0.06
     classroom
    -0.06
    !.↵↵
    -0.06
    POSITIVE LOGITS
    Quarter
    0.06
    Stencil
    0.06
     Mate
    0.06
     Phật
    0.06
    .createCell
    0.06
    orgt
    0.06
    hare
    0.06
     �
    0.06
     लड
    0.06
    getNext
    0.06
    Act Density 0.017%

    No Known Activations