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

    Neuronpedia

    INDEX
    Explanations

    judgment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     crystall
    -0.06
     mane
    -0.06
    eded
    -0.06
    Ability
    -0.06
    �
    -0.06
    hot
    -0.05
    Как
    -0.05
    айд
    -0.05
     dominate
    -0.05
    POSITIVE LOGITS
    .sound
    0.08
     OSD
    0.07
    (Collections
    0.07
    (cpu
    0.07
    .↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    afety
    0.07
    -routing
    0.07
     redevelopment
    0.06
     公
    0.06
    avatar
    0.06
    Act Density 0.010%

    No Known Activations