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

    Neuronpedia

    INDEX
    Explanations

    Internet discussions/blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    less
    -0.07
     looked
    -0.07
     secrets
    -0.06
    overlay
    -0.06
     blue
    -0.06
    .Game
    -0.06
     State
    -0.06
    „ط
    -0.06
    herent
    -0.06
    .other
    -0.06
    POSITIVE LOGITS
     كس
    0.06
    -Feb
    0.06
     combating
    0.06
     正
    0.06
     tổn
    0.06
    億
    0.06
    (ib
    0.06
     hạng
    0.06
     �
    0.06
     kutje
    0.06
    Act Density 0.022%

    No Known Activations