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

    Neuronpedia

    INDEX
    Explanations

    share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    à¸ķรา
    -0.27
    ÊĬ
    -0.25
     undes
    -0.25
    alent
    -0.24
    /platform
    -0.24
    urry
    -0.24
    /button
    -0.24
    Ĥ¬
    -0.24
    æķ°åŃĹåĮĸ
    -0.24
    ç¼ij
    -0.24
    POSITIVE LOGITS
    NAS
    0.29
    rin
    0.27
    ospace
    0.27
    slice
    0.26
     bis
    0.25
    代çIJĨ
    0.25
     slice
    0.25
    din
    0.24
     dyn
    0.24
     Swap
    0.24
    Act Density 0.004%

    No Known Activations