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

    Neuronpedia

    INDEX
    Explanations

    navigational intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    都已经
    0.45
    侣
    0.44
     તેઓ
    0.42
     언급
    0.42
     fondness
    0.42
    螺
    0.42
    可以说
    0.42
    汇
    0.42
     hopelessness
    0.42
     ആരോപ
    0.41
    POSITIVE LOGITS
     five
    0.48
     ऑक्साइड
    0.47
     nine
    0.46
    fraction
    0.45
     fractional
    0.44
     eight
    0.44
     six
    0.42
    5
    0.42
     daily
    0.41
     Merck
    0.40
    Act Density 0.003%

    No Known Activations