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

    Neuronpedia

    INDEX
    Explanations

    Prime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sullivan
    -0.08
    ullivan
    -0.08
    C
    -0.07
     Hab
    -0.07
     Saw
    -0.07
     Cow
    -0.06
    (suffix
    -0.06
     Garten
    -0.06
    _accessor
    -0.06
     inhal
    -0.06
    POSITIVE LOGITS
     Prime
    0.17
     prime
    0.17
    Prime
    0.14
     primes
    0.11
    пи
    0.10
     Prim
    0.09
     prim
    0.09
     Crimson
    0.09
    prime
    0.09
    _prime
    0.08
    Act Density 0.018%

    No Known Activations