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

    Neuronpedia

    INDEX
    Explanations

    scientific publication supplementary information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wipes
    -0.07
    ווי
    -0.07
    旞
    -0.07
     possessing
    -0.07
    ствовать
    -0.07
    vit
    -0.07
    提炼
    -0.06
     multif
    -0.06
     laughing
    -0.06
    ရ
    -0.06
    POSITIVE LOGITS
    Batman
    0.08
     🙂↵↵
    0.07
     biologist
    0.07
    iband
    0.07
     blurred
    0.07
    病房
    0.07
    楽
    0.07
    irim
    0.07
    얀
    0.07
    .Module
    0.06
    Act Density 0.000%

    No Known Activations