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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     America
    -0.07
    .processor
    -0.07
    nth
    -0.07
     Brid
    -0.07
     bộ
    -0.07
     लाग
    -0.06
     अर्ज
    -0.06
    ...',↵
    -0.06
    .invalidate
    -0.06
     affiliates
    -0.06
    POSITIVE LOGITS
     locked
    0.16
     Locked
    0.15
     verrou
    0.15
    Immutable
    0.15
     rigidity
    0.14
    Locked
    0.14
    被冻结
    0.14
    locked
    0.13
     locking
    0.13
    Readonly
    0.13
    Act Density 0.038%

    No Known Activations