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

    Neuronpedia

    INDEX
    Explanations

    authentication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .only
    -0.07
     Bun
    -0.07
     foo
    -0.06
     Mary
    -0.06
     `<
    -0.06
    ql
    -0.06
     bunların
    -0.06
     ime
    -0.06
     Razor
    -0.06
     weiber
    -0.06
    POSITIVE LOGITS
     Моск
    0.06
    Listening
    0.06
     ExecutionContext
    0.06
     Hire
    0.06
    切り
    0.06
     fossils
    0.06
     comfy
    0.06
     sincerely
    0.06
     Applications
    0.06
    Gamma
    0.06
    Act Density 0.005%

    No Known Activations