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

    Neuronpedia

    INDEX
    Explanations

    actions to achieve goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.35
     \
    0.33
     più
    0.30
     or
    0.29
     혹은
    0.29
     ​
    0.29
    л
    0.28
     &
    0.27
     Maduro
    0.26
     Sü
    0.26
    POSITIVE LOGITS
     creating
    0.47
     achieving
    0.44
     obtaining
    0.43
     providing
    0.42
     finding
    0.41
     attaining
    0.41
     maintaining
    0.40
     applying
    0.40
     assembling
    0.39
     bringing
    0.38
    Act Density 0.474%

    No Known Activations