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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     norms
    -0.07
    FIX
    -0.07
     dips
    -0.07
     caramel
    -0.07
     gep
    -0.06
    bek
    -0.06
     absorbs
    -0.06
     configs
    -0.06
    ใหม
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    *",
    0.07
     Of
    0.07
    JPEG
    0.07
    Footer
    0.06
     zx
    0.06
    numeric
    0.06
    disable
    0.06
    」，
    0.06
    submit
    0.06
     of
    0.06
    Act Density 0.014%

    No Known Activations