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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ；
    -0.08
     pomocí
    -0.07
     style
    -0.07
    close
    -0.07
     Olympus
    -0.07
     productive
    -0.07
     všech
    -0.07
    -element
    -0.07
     multiple
    -0.07
     twin
    -0.07
    POSITIVE LOGITS
    ",__
    0.06
    
    0.06
     /^
    0.06
    .singletonList
    0.06
    (gs
    0.06
    กระ
    0.06
     pož
    0.06
    kového
    0.06
     '-')↵
    0.06
    ะ
    0.06
    Act Density 0.121%

    No Known Activations