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

    Neuronpedia

    INDEX
    Explanations

    de/of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     providedIn
    -0.08
    AuthGuard
    -0.08
    вис
    -0.07
    blick
    -0.07
    祜
    -0.07
    蘼
    -0.07
    child
    -0.07
     vulner
    -0.07
    姹
    -0.07
    缡
    -0.07
    POSITIVE LOGITS
    훝
    0.08
    LOTS
    0.07
    >");↵↵
    0.07
     Jays
    0.07
    )`↵
    0.07
    ")))↵
    0.07
    ())))↵
    0.06
    洘
    0.06
    其实就是
    0.06
    منظم
    0.06
    Act Density 0.005%

    No Known Activations