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

    Neuronpedia

    INDEX
    Explanations

    comet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Windsor
    -0.07
     Weeks
    -0.07
    Boy
    -0.06
    fr
    -0.06
     Wife
    -0.06
     Wochen
    -0.06
     Pearson
    -0.06
    Skills
    -0.06
    Hands
    -0.06
     Hra
    -0.06
    POSITIVE LOGITS
     comet
    0.10
    Containing
    0.08
     التح
    0.06
    selected
    0.06
    знача
    0.06
    \Post
    0.06
    .onError
    0.06
     unde
    0.06
    mi
    0.06
    кування
    0.06
    Act Density 0.002%

    No Known Activations