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

    Neuronpedia

    INDEX
    Explanations

    of these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    حدى
    0.28
    Rising
    0.27
    bare
    0.25
    Shop
    0.24
    Trail
    0.24
    Room
    0.24
    bone
    0.23
     jednego
    0.23
    yield
    0.23
    Salah
    0.23
    POSITIVE LOGITS
     whom
    0.42
     course
    0.35
     which
    0.34
     them
    0.29
     которых
    0.28
     whiche
    0.28
     них
    0.27
     którym
    0.26
     ambayo
    0.25
     malah
    0.25
    Act Density 0.011%

    No Known Activations