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

    Neuronpedia

    INDEX
    Explanations

    Code and markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lighting
    -0.10
    Lighting
    -0.10
    灯
    -0.10
     dermat
    -0.10
     Dolby
    -0.09
     Dermat
    -0.09
     Lighting
    -0.09
     wavelengths
    -0.09
     bitter
    -0.09
     отоп
    -0.08
    POSITIVE LOGITS
    .Array
    0.13
    .Arrays
    0.12
    \Array
    0.12
     storing
    0.12
    数组
    0.12
     Speicher
    0.11
    存
    0.11
    .array
    0.11
     associative
    0.11
    deque
    0.11
    Act Density 0.036%

    No Known Activations