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

    Neuronpedia

    INDEX
    Explanations

    understanding water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     broken
    0.36
     hanya
    0.34
     prowess
    0.33
     abstraction
    0.33
     loophole
    0.33
     mode
    0.33
     forced
    0.32
     com
    0.32
     kwa
    0.32
    mode
    0.32
    POSITIVE LOGITS
    Understand
    0.52
    Water
    0.51
    Understanding
    0.50
     Martine
    0.49
     Understand
    0.49
    You
    0.49
    Aqu
    0.49
    Your
    0.49
    Hiking
    0.48
    <unused1167>
    0.47
    Act Density 4.917%

    No Known Activations