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

    Neuronpedia

    INDEX
    Explanations

    Destroyer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BuildContext
    -0.07
    움
    -0.07
    흥
    -0.07
    이라
    -0.06
    瞬
    -0.06
    ()).
    -0.06
    ペ
    -0.06
    testCase
    -0.06
     MyClass
    -0.06
    oldt
    -0.06
    POSITIVE LOGITS
    juries
    0.07
    amount
    0.07
    sorting
    0.07
    Acceler
    0.06
     Throws
    0.06
    .ones
    0.06
    Opens
    0.06
    ướ
    0.06
    verbatim
    0.06
     alloc
    0.06
    Act Density 0.009%

    No Known Activations