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

    Neuronpedia

    INDEX
    Explanations

    Circuit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VERBOSE
    -0.07
     verbose
    -0.06
     yandan
    -0.06
    (mc
    -0.06
     spoke
    -0.06
     citations
    -0.06
    .serialize
    -0.06
    ことは
    -0.06
    .Operator
    -0.06
     ψ
    -0.06
    POSITIVE LOGITS
     Brain
    0.07
     Put
    0.07
     writ
    0.06
     κατά
    0.06
    に向
    0.06
     kittens
    0.06
     diminished
    0.06
     động
    0.06
    athan
    0.06
     }*/↵
    0.06
    Act Density 0.002%

    No Known Activations