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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ................
    -0.07
     markings
    -0.06
    ังกล
    -0.06
    atrigesimal
    -0.06
    COMP
    -0.06
    782
    -0.06
    _vect
    -0.06
    earer
    -0.06
     Develop
    -0.06
     sırasında
    -0.06
    POSITIVE LOGITS
    .Popen
    0.07
     Nat
    0.07
     Nit
    0.07
     Phillies
    0.07
     same
    0.06
    -Se
    0.06
     hacker
    0.06
     Candid
    0.06
     лю
    0.06
    /math
    0.06
    Act Density 0.001%

    No Known Activations