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

    Neuronpedia

    INDEX
    Explanations

    commas and "I"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uo
    -0.07
     catapult
    -0.06
     ва
    -0.06
     cosplay
    -0.06
     neighbor
    -0.06
     Wagner
    -0.06
     Hawk
    -0.06
     network
    -0.06
     connection
    -0.06
    akening
    -0.06
    POSITIVE LOGITS
    Poly
    0.07
    .zh
    0.06
     ポ
    0.06
     "))
    0.06
    [];
↵
    0.06
     verbally
    0.06
     Irvine
    0.06
    KNOWN
    0.06
     Synd
    0.06
     пром
    0.06
    Act Density 0.240%

    No Known Activations