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

    Neuronpedia

    INDEX
    Explanations

    code/urls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     přísluš
    -0.07
    陵
    -0.06
     resembling
    -0.06
     zlib
    -0.06
    .bc
    -0.06
     помощью
    -0.06
     Bras
    -0.06
     utf
    -0.06
     nicer
    -0.06
    円
    -0.06
    POSITIVE LOGITS
     weaving
    0.07
     Herz
    0.07
     may
    0.06
    eck
    0.06
    오
    0.06
    (EXIT
    0.06
    BASH
    0.06
     Suarez
    0.06
    (File
    0.06
    (remove
    0.06
    Act Density 0.000%

    No Known Activations