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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nướng
    -0.07
    dığında
    -0.06
     salmon
    -0.06
     خرد
    -0.06
    	number
    -0.06
     Jenner
    -0.06
    butt
    -0.06
    ffa
    -0.06
     dope
    -0.06
     перет
    -0.06
    POSITIVE LOGITS
     so
    0.08
     Yah
    0.07
     ハ
    0.07
     Illegal
    0.07
     LOW
    0.07
     alloc
    0.07
    ホ
    0.06
     StringField
    0.06
    ="<?=$
    0.06
    <S
    0.06
    Act Density 0.049%

    No Known Activations