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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yasal
    -0.07
     geçerli
    -0.07
    ADF
    -0.07
     Till
    -0.07
     plo
    -0.06
     herk
    -0.06
     taxonomy
    -0.06
     rab
    -0.06
     army
    -0.06
     /(
    -0.06
    POSITIVE LOGITS
    TES
    0.07
     dont
    0.07
    dont
    0.07
    international
    0.06
    sing
    0.06
    영어
    0.06
    benef
    0.06
    only
    0.06
    lene
    0.06
     разных
    0.06
    Act Density 0.024%

    No Known Activations