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

    Neuronpedia

    INDEX
    Explanations

    category followed by specific descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PwC
    0.47
     CFRP
    0.47
     chloroplast
    0.45
     FPGA
    0.45
     GFP
    0.44
     TOEFL
    0.43
     postmodern
    0.43
     phytoplankton
    0.42
     NAACP
    0.41
     четы
    0.41
    POSITIVE LOGITS
    (
    0.84
    :
    0.71
    -
    0.65
    =
    0.61
    .
    0.50
    اتی
    0.50
    {
    0.49
    )
    0.48
    ス
    0.47
     (
    0.47
    Act Density 2.817%

    No Known Activations