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

    Neuronpedia

    INDEX
    Explanations

    math/graph theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waffle
    -0.08
     निवेश
    -0.08
    ettua
    -0.08
     mastering
    -0.08
    iriye
    -0.07
     WRITE
    -0.07
    .ticket
    -0.07
     Monsanto
    -0.07
     Zillow
    -0.07
     leveren
    -0.07
    POSITIVE LOGITS
    剩
    0.15
    Remaining
    0.14
     remaining
    0.14
    _remaining
    0.14
     Removing
    0.14
    Removing
    0.14
     verble
    0.14
     Remaining
    0.13
    remaining
    0.13
     restantes
    0.13
    Act Density 0.048%

    No Known Activations