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

    Neuronpedia

    INDEX
    Explanations

    term followed by state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    బ్బ
    0.71
     তৃণ
    0.71
     Nghị
    0.70
    頖
    0.68
    vorschau
    0.67
    ্যাম
    0.65
     अय्यर
    0.63
     प्रतिभाग
    0.63
    티브
    0.62
    ünk
    0.62
    POSITIVE LOGITS
     state
    6.14
    state
    5.66
     State
    5.28
    State
    5.26
     estado
    5.01
     states
    4.92
    状态
    4.71
     STATE
    4.65
    STATE
    4.64
    狀態
    4.47
    Act Density 0.719%

    No Known Activations