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

    Neuronpedia

    INDEX
    Explanations

    fold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    应该
    -0.06
     ix
    -0.06
    .utf
    -0.06
     Tue
    -0.06
     zam
    -0.06
    	fprintf
    -0.06
    家
    -0.06
     mart
    -0.06
    .upper
    -0.06
    _asc
    -0.06
    POSITIVE LOGITS
     aggressively
    0.07
    拥
    0.07
    .Rest
    0.07
    ewitness
    0.07
    ヒ
    0.07
    .Package
    0.07
     Mockito
    0.07
    ্�
    0.07
     Monster
    0.07
    \Customer
    0.06
    Act Density 0.003%

    No Known Activations