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

    Neuronpedia

    INDEX
    Explanations

    caching strategies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quartet
    -0.09
     brutality
    -0.09
     feminine
    -0.08
     drafted
    -0.08
     unh
    -0.08
     fireworks
    -0.08
    _pose
    -0.08
     ballroom
    -0.08
    _FW
    -0.08
     diploma
    -0.08
    POSITIVE LOGITS
    缓存
    0.26
     caching
    0.25
     cache
    0.23
    Caching
    0.23
    Cache
    0.22
    .cache
    0.22
    cache
    0.22
     caches
    0.21
    	cache
    0.21
    _cache
    0.21
    Act Density 0.014%

    No Known Activations