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

    Neuronpedia

    INDEX
    Explanations

    describe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.82
    AndEndTag
    -0.77
     description
    -0.67
    expandindo
    -0.67
     ब्रेकडाउन
    -0.66
    ViewImports
    -0.66
    Билгалдахарш
    -0.64
    Erreferentziak
    -0.64
    "}"
    -0.63
     descrizione
    -0.63
    POSITIVE LOGITS
     foramen
    0.49
    rrh
    0.48
     urch
    0.47
     laurel
    0.47
    hasMoreElements
    0.46
     tongues
    0.45
     eagles
    0.45
     bees
    0.45
     geodes
    0.45
     reeds
    0.44
    Act Density 0.022%

    No Known Activations