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

    Neuronpedia

    INDEX
    Explanations

    cache

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    numbers
    -0.07
     Clifford
    -0.07
     spots
    -0.07
     Ung
    -0.07
     structs
    -0.06
     STL
    -0.06
     Starr
    -0.06
     möchten
    -0.06
     slips
    -0.06
    arrays
    -0.06
    POSITIVE LOGITS
    Cache
    0.10
     cache
    0.09
    cache
    0.08
    ACE
    0.08
     Cache
    0.08
    Rachel
    0.08
     CACHE
    0.08
    _cache
    0.08
     Rachel
    0.07
    oise
    0.07
    Act Density 0.009%

    No Known Activations