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

    Neuronpedia

    INDEX
    Explanations

    null

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    なお
    -0.07
     aluno
    -0.07
     chlap
    -0.07
     very
    -0.07
     Evropské
    -0.07
    	TR
    -0.06
     política
    -0.06
     Thomson
    -0.06
    cot
    -0.06
    	common
    -0.06
    POSITIVE LOGITS
     Null
    0.10
     null
    0.07
    Null
    0.07
    ус
    0.07
    는다
    0.07
    -null
    0.07
    idi
    0.06
    ed
    0.06
     mattresses
    0.06
    .ArrayList
    0.06
    Act Density 0.009%

    No Known Activations