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

    Neuronpedia

    INDEX
    Explanations

    movie plot summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poser
    -0.07
    関係
    -0.07
    208
    -0.07
     ว
    -0.06
     ΕΠ
    -0.06
    -plugin
    -0.06
    Merge
    -0.06
     činnost
    -0.06
    strcasecmp
    -0.06
    	filename
    -0.06
    POSITIVE LOGITS
    carbon
    0.06
    FTA
    0.06
     Destruction
    0.06
     первого
    0.06
    ρκ
    0.06
     м
    0.06
    .Design
    0.06
     BCHP
    0.06
    .rot
    0.06
     інозем
    0.06
    Act Density 0.107%

    No Known Activations