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

    Neuronpedia

    INDEX
    Explanations

    Phonetics and phonology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sou
    -0.07
     jíd
    -0.06
    antiago
    -0.06
    _SEQUENCE
    -0.06
     injections
    -0.06
     Lumpur
    -0.05
     SUN
    -0.05
     GX
    -0.05
    170
    -0.05
    Snap
    -0.05
    POSITIVE LOGITS
     phon
    0.08
    舍
    0.07
     Phon
    0.07
    _concat
    0.06
    .Throws
    0.06
     dropout
    0.06
    =logging
    0.06
    (E
    0.06
    semblies
    0.06
    (vo
    0.06
    Act Density 0.003%

    No Known Activations