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

    Neuronpedia

    INDEX
    Explanations

    computer science and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clash
    -0.08
     freckles
    -0.08
     வய
    -0.08
     luyện
    -0.08
     finde
    -0.08
    итися
    -0.08
     lips
    -0.08
    ไว
    -0.07
     Kern
    -0.07
     Cowboy
    -0.07
    POSITIVE LOGITS
    .tasks
    0.07
     tera
    0.07
     বাজ
    0.07
    .Art
    0.07
     sanction
    0.07
     inspiring
    0.07
     अग्र
    0.06
    联盟
    0.06
    .Health
    0.06
    atia
    0.06
    Act Density 0.000%

    No Known Activations