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

    Neuronpedia

    INDEX
    Explanations

    "found", "present", "introduced"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ึ้น
    -0.09
    Where
    -0.08
    où
    -0.07
     สำหรับ
    -0.07
    थे
    -0.07
     pẹlu
    -0.07
     capables
    -0.07
     कोई
    -0.07
    ाँ
    -0.07
     Where
    -0.07
    POSITIVE LOGITS
     الموجودة
    0.30
     found
    0.29
     الموجود
    0.29
     present
    0.26
     presenti
    0.25
     introduced
    0.24
    	found
    0.24
     discovered
    0.24
     contained
    0.23
     présents
    0.23
    Act Density 0.354%

    No Known Activations