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

    Neuronpedia

    INDEX
    Explanations

    Translation with terms unchanged

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    इत
    -0.09
    म्भ
    -0.08
     fullness
    -0.08
    त्तर
    -0.08
     Regular
    -0.08
    想着
    -0.07
    स्या
    -0.07
     profunda
    -0.07
    Histogram
    -0.07
     नियमित
    -0.07
    POSITIVE LOGITS
     unchanged
    0.12
     unaffected
    0.11
     그대로
    0.10
     untranslated
    0.09
     translated
    0.08
    English
    0.08
     Zahlen
    0.08
     ഇംഗ്ല
    0.08
     English
    0.08
    Arabic
    0.08
    Act Density 0.022%

    No Known Activations