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

    Neuronpedia

    INDEX
    Explanations

    court rule numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Byte
    -0.07
    ($('<
    -0.07
    .Enter
    -0.07
     shiny
    -0.07
    Forg
    -0.06
    hydro
    -0.06
    mmm
    -0.06
     alacak
    -0.06
    ersive
    -0.06
     Reader
    -0.06
    POSITIVE LOGITS
     ########################
    0.07
     Implements
    0.07
    GIN
    0.06
    發
    0.06
    ...↵
    0.06
     Down
    0.06
     exploits
    0.06
     veterinarian
    0.06
     پایه
    0.06
    填
    0.06
    Act Density 0.011%

    No Known Activations