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

    Neuronpedia

    INDEX
    Explanations

    long-term planning or strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     summand
    0.45
     FPGA
    0.42
    ኾ
    0.41
     spectrogram
    0.41
     Calcula
    0.40
     Histogram
    0.39
    ÇÃO
    0.39
     derivative
    0.39
     derived
    0.38
    এর
    0.38
    POSITIVE LOGITS
    ...
    0.45
    en
    0.44
    "
    0.44
    direct
    0.42
    (?)
    0.42
    -
    0.42
    '/>
    0.41
    obe
    0.41
    either
    0.40
    neither
    0.40
    Act Density 0.431%

    No Known Activations