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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detail
    -0.08
     kil
    -0.07
    akah
    -0.07
     leg
    -0.07
    brief
    -0.07
    /wiki
    -0.06
     sung
    -0.06
    徒
    -0.06
    along
    -0.06
     rect
    -0.06
    POSITIVE LOGITS
     accepted
    0.06
    .Future
    0.06
    .IsChecked
    0.06
     никто
    0.06
     believes
    0.06
    .isHidden
    0.06
     abst
    0.06
    谁
    0.06
     Venezuelan
    0.06
     кілька
    0.06
    Act Density 0.041%

    No Known Activations