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

    Neuronpedia

    INDEX
    Explanations

    imported as a module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Group
    0.45
    please
    0.41
    service
    0.40
     定义
    0.40
    ovec
    0.40
     몸
    0.39
    volve
    0.39
    Compet
    0.39
    om
    0.38
    other
    0.38
    POSITIVE LOGITS
     одним
    0.44
    போ
    0.44
    izat
    0.42
     Elephant
    0.42
     onto
    0.41
    т
    0.41
    }°
    0.40
    czny
    0.40
     vào
    0.40
    জ্জ
    0.40
    Act Density 0.001%

    No Known Activations