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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .chdir
    -0.07
    prim
    -0.07
     Alta
    -0.07
    ald
    -0.06
    Redux
    -0.06
     main
    -0.06
    datal
    -0.06
     handed
    -0.06
    External
    -0.06
    TECTION
    -0.06
    POSITIVE LOGITS
     VAR
    0.08
     dg
    0.07
     forgotten
    0.06
    рович
    0.06
    алізації
    0.06
    芝
    0.06
     Druh
    0.06
     completes
    0.06
     platí
    0.06
    �
    0.06
    Act Density 0.017%

    No Known Activations