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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ปลอดภ
    -0.08
     stupidity
    -0.07
     demonstration
    -0.07
    	onChange
    -0.07
     Hats
    -0.07
     cũng
    -0.06
    ponential
    -0.06
     دیده
    -0.06
    -data
    -0.06
     verbess
    -0.06
    POSITIVE LOGITS
    ordion
    0.06
    ult
    0.06
    ンタ
    0.06
     ]),↵
    0.06
    (DEBUG
    0.06
    _SPLIT
    0.06
     MSG
    0.06
    �
    0.06
    ﾞ
    0.06
    rix
    0.05
    Act Density 0.042%

    No Known Activations