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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glyphicon
    -1.17
     Paglinawan
    -1.11
    UCHAR
    -1.00
    COMM
    -0.96
    डा
    -0.95
    anging
    -0.90
     stringent
    -0.90
    теро
    -0.90
     [],
    -0.89
    IZER
    -0.88
    POSITIVE LOGITS
     before
    1.06
    kadang
    1.03
     trozos
    1.01
     concursos
    0.99
    Én
    0.98
     muñecas
    0.97
    geç
    0.93
     alojamientos
    0.93
     japones
    0.92
     salarios
    0.91
    Act Density 0.016%

    No Known Activations