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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sebelum
    0.76
    ($"
    0.70
    Pa
    0.69
    ($"{
    0.67
    tmp
    0.64
    $=\
    0.63
    Couple
    0.63
    ১৪
    0.63
     نئی
    0.63
    Var
    0.63
    POSITIVE LOGITS
    1.53
     five
    1.07
     exactly
    1.04
     ten
    0.98
    <unused2155>
    0.96
     six
    0.95
     fifty
    0.94
     approximately
    0.94
     nine
    0.94
     thirty
    0.94
    Act Density 1.508%

    No Known Activations