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

    Neuronpedia

    INDEX
    Explanations

    programming code syntax

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wajib
    0.60
     کیوں
    0.57
    阻塞
    0.56
    鐨
    0.53
     regulate
    0.52
     স্বল্প
    0.52
    regex
    0.52
     Regex
    0.51
     limiting
    0.51
    getvalue
    0.51
    POSITIVE LOGITS
     ={
    0.76
    ={()
    0.73
    =’
    0.73
    ='/
    0.71
    ={}
    0.69
    ={
    0.66
     ='
    0.66
    ≅
    0.64
    ='
    0.64
    ={},
    0.63
    Act Density 0.000%

    No Known Activations