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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Same
    -0.07
    ]$
    -0.07
     communication
    -0.07
    ustum
    -0.06
     departure
    -0.06
     attend
    -0.06
    90
    -0.06
     performing
    -0.06
    ków
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    .tie
    0.07
    �除
    0.06
     сент
    0.06
     tariffs
    0.06
     розп
    0.06
    NSInteger
    0.06
    ニﾆ
    0.06
    LEMENT
    0.06
    šker
    0.06
     Exam
    0.06
    Act Density 0.004%

    No Known Activations