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

    Neuronpedia

    INDEX
    Explanations

    sorting, initialization, operator, encoding, backslash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avenir
    0.70
     collagen
    0.70
     flyer
    0.69
     Collagen
    0.68
     conseiller
    0.66
    কাঠ
    0.66
     SDG
    0.66
     pegatina
    0.66
     affluent
    0.65
     paid
    0.63
    POSITIVE LOGITS
    初始化
    1.01
     initialization
    1.00
    运算符
    1.00
     initialize
    0.99
     `{
    0.98
    <0x1C>
    0.95
     deserial
    0.94
     (`
    0.94
     Initialization
    0.94
     initializes
    0.93
    Act Density 0.142%

    No Known Activations