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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quienes
    -0.07
    ới
    -0.07
     hazardous
    -0.06
    UGINS
    -0.06
     vend
    -0.06
    力的
    -0.06
     diplom
    -0.06
    ịp
    -0.06
     newNode
    -0.06
     но
    -0.06
    POSITIVE LOGITS
    chunk
    0.07
    dsp
    0.06
    Sexy
    0.06
    ".$
    0.06
    pared
    0.06
    _matrix
    0.06
     ^↵
    0.06
    ZeroWidthSpace
    0.06
    wel
    0.06
    ेष
    0.06
    Act Density 0.274%

    No Known Activations