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

    Neuronpedia

    INDEX
    Explanations

    story excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     два
    -0.07
     wang
    -0.06
     Ful
    -0.06
     Than
    -0.06
     ive
    -0.06
    	pos
    -0.06
     Passing
    -0.06
     specialties
    -0.06
    」と
    -0.06
     lem
    -0.06
    POSITIVE LOGITS
    件事
    0.07
    PointCloud
    0.07
     Tanrı
    0.07
    ▋▋
    0.07
    rodní
    0.07
    DeltaTime
    0.07
     manned
    0.06
    ony
    0.06
     �
    0.06
     Difficulty
    0.06
    Act Density 0.003%

    No Known Activations