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

    Neuronpedia

    INDEX
    Explanations

    Final Answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Somehow
    0.47
     Hints
    0.42
     Hint
    0.40
     somehow
    0.39
     Due
    0.39
     Any
    0.38
     След
    0.38
     Asking
    0.38
     Huskies
    0.38
     เนื่องจาก
    0.38
    POSITIVE LOGITS
    linear
    0.37
    chakra
    0.36
     otro
    0.35
    تص
    0.35
    holm
    0.35
    ρά
    0.35
    另一个
    0.35
    دور
    0.35
    progressive
    0.35
    Furniture
    0.35
    Act Density 0.000%

    No Known Activations