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

    Neuronpedia

    INDEX
    Explanations

    result or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असून
    0.36
    ませんが
    0.32
    اہد
    0.31
     pembelajaran
    0.30
     وګ
    0.30
     mutta
    0.30
    していますが
    0.30
     없고
    0.29
     melibatkan
    0.29
     graag
    0.29
    POSITIVE LOGITS
    。
    0.49
    ).
    0.39
    ።
    0.39
    .*
    0.37
    ។
    0.37
     Thus
    0.35
    thus
    0.35
    从而
    0.32
    Thus
    0.31
    Ainsi
    0.31
    Act Density 0.475%

    No Known Activations