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

    Neuronpedia

    INDEX
    Explanations

    Research findings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    倕
    -0.07
     anesthesia
    -0.07
     education
    -0.07
    爱国主义
    -0.07
     рын
    -0.07
     Encoding
    -0.07
    发明专利
    -0.07
    .Consumer
    -0.07
    Elapsed
    -0.07
     Depos
    -0.07
    POSITIVE LOGITS
     Ranger
    0.07
     Rim
    0.07
     hopping
    0.07
    .Multi
    0.07
    finder
    0.07
     soundtrack
    0.07
    锆
    0.06
    )>>
    0.06
     fotoğraf
    0.06
     sax
    0.06
    Act Density 0.051%

    No Known Activations