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

    Neuronpedia

    INDEX
    Explanations

    account of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Egg
    0.47
     sẽ
    0.45
     Performing
    0.44
     akan
    0.43
     Negeri
    0.43
    返回
    0.43
     уви
    0.42
    o
    0.42
    会
    0.42
    0.42
    POSITIVE LOGITS
     divs
    0.54
    ieva
    0.50
    <unused40>
    0.50
    たちが
    0.49
    0.49
    ⟋
    0.49
    astres
    0.48
    𝟰
    0.48
     だっ
    0.47
    ()];
    0.47
    Act Density 0.001%

    No Known Activations