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

    Neuronpedia

    INDEX
    Explanations

    immature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     코
    -0.07
     WD
    -0.07
     favourable
    -0.07
    kd
    -0.06
    posting
    -0.06
    uç
    -0.06
     zona
    -0.06
    arias
    -0.06
    کور
    -0.06
    King
    -0.06
    POSITIVE LOGITS
     immature
    0.09
     irresponsible
    0.07
     childish
    0.07
                               ↵
    0.06
              ↵
    0.06
    .SceneManagement
    0.06
    Status
    0.06
     camar
    0.06
     childcare
    0.06
     nevě
    0.06
    Act Density 0.003%

    No Known Activations