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

    Neuronpedia

    INDEX
    Explanations

    --

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medically
    -0.06
    ow
    -0.06
    III
    -0.06
     tedy
    -0.06
    堆
    -0.06
    DataType
    -0.06
    fast
    -0.06
    	idx
    -0.06
     wy
    -0.06
    _since
    -0.06
    POSITIVE LOGITS
     primaries
    0.07
    几个
    0.06
     victim
    0.06
     jTable
    0.06
     insan
    0.06
     बद
    0.06
    ają
    0.06
    ICC
    0.06
     eager
    0.06
    +c
    0.06
    Act Density 0.002%

    No Known Activations