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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     downstairs
    -0.08
     wiring
    -0.08
     dismant
    -0.08
     abas
    -0.08
     Quot
    -0.07
     يف
    -0.07
     liefst
    -0.07
    输
    -0.07
     logisch
    -0.07
     verständ
    -0.07
    POSITIVE LOGITS
     fontsize
    0.11
    (size
    0.11
    -size
    0.11
     CGSize
    0.11
     sized
    0.10
    =size
    0.10
    fontsize
    0.10
    Sized
    0.10
     tamaños
    0.10
     आकार
    0.10
    Act Density 0.003%

    No Known Activations