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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    范围
    -0.06
    ところ
    -0.06
     freaking
    -0.06
    話
    -0.06
    >T
    -0.06
     Vale
    -0.06
    	element
    -0.06
     volum
    -0.06
     Ch
    -0.06
     puan
    -0.06
    POSITIVE LOGITS
    spl
    0.08
    	now
    0.07
    ंप
    0.06
     comun
    0.06
    Partition
    0.06
    criminal
    0.06
    CellValue
    0.06
     spl
    0.06
     شهرد
    0.06
     Professionals
    0.06
    Act Density 0.164%

    No Known Activations