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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tät
    -0.08
     viên
    -0.08
    成果
    -0.08
    -0.08
    �
    -0.08
     vandal
    -0.08
     Metropolitana
    -0.08
     lum
    -0.08
     voli
    -0.08
     கே
    -0.07
    POSITIVE LOGITS
     burden
    0.08
    ناک
    0.08
    pok
    0.08
     Bruder
    0.08
    नाक
    0.07
     acorde
    0.07
     crust
    0.07
     intense
    0.07
     experienced
    0.07
     felt
    0.07
    Act Density 0.011%
    No Known Activations