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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detach
    -0.07
     mActivity
    -0.07
    ChildScrollView
    -0.07
     *
↵
    -0.06
     krij
    -0.06
    .have
    -0.06
     hace
    -0.06
     *)[
    -0.06
     sunrise
    -0.06
    gist
    -0.06
    POSITIVE LOGITS
     hunting
    0.07
    Gro
    0.06
     механи
    0.06
    -caret
    0.06
     zvý
    0.06
     Hunt
    0.06
    LESS
    0.06
    .Types
    0.06
     Enjoy
    0.06
     petits
    0.06
    Act Density 0.003%

    No Known Activations