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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sensitive
    -0.07
    春
    -0.07
    ेद
    -0.06
     vines
    -0.06
    269
    -0.06
     setUser
    -0.06
     peanuts
    -0.06
     inactive
    -0.06
    377
    -0.06
     FALL
    -0.06
    POSITIVE LOGITS
     можуть
    0.07
     часто
    0.07
     CORPOR
    0.07
     ジ
    0.07
     scr
    0.06
    <=
    0.06
    ��
    0.06
     Дж
    0.06
     داستان
    0.06
    }});↵
    0.06
    Act Density 0.103%

    No Known Activations