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

    Neuronpedia

    INDEX
    Explanations

    the market

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungy
    0.42
    decode
    0.39
    Gates
    0.37
    aughters
    0.37
    pairs
    0.36
    ラック
    0.36
    quat
    0.36
    jump
    0.36
    embark
    0.36
    rack
    0.36
    POSITIVE LOGITS
     Read
    0.45
    Read
    0.42
    밖에
    0.41
     Bub
    0.41
     bubbles
    0.38
    Leer
    0.38
     Valentino
    0.38
     yas
    0.38
     மா
    0.38
     Grassmann
    0.37
    Act Density 0.000%

    No Known Activations