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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    calloc
    -0.09
    (cookie
    -0.09
     calloc
    -0.09
    Lottery
    -0.09
     gambling
    -0.08
     literacy
    -0.08
    Cookie
    -0.08
     fizz
    -0.08
    Produtos
    -0.08
     cookies
    -0.08
    POSITIVE LOGITS
     minimizing
    0.12
     minimizar
    0.11
     pedestrians
    0.10
     minimize
    0.10
    .distance
    0.10
     दूरी
    0.10
     reposition
    0.09
    距离
    0.09
    徒歩
    0.09
     distance
    0.09
    Act Density 0.030%

    No Known Activations