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

    Neuronpedia

    INDEX
    Explanations

    hypercar, capital, capacity, strategic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اک
    0.55
    يج
    0.50
    ক
    0.50
    ᱸ
    0.50
    ат
    0.50
    ర్
    0.49
    ière
    0.49
    知道了
    0.49
    𝚋
    0.49
    к
    0.49
    POSITIVE LOGITS
     de
    0.55
     il
    0.55
     enkel
    0.54
     drifts
    0.51
     lud
    0.50
     sparsim
    0.49
    de
    0.48
     vil
    0.48
     ferment
    0.48
     sv
    0.47
    Act Density 0.000%

    No Known Activations