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

    Neuronpedia

    INDEX
    Explanations

    financial, time, national

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нико
    0.42
     नपु
    0.40
    oretum
    0.39
     restable
    0.39
    ლებიც
    0.39
    ទេ
    0.38
     tránsito
    0.38
     नव्हते
    0.38
    PUBLIC
    0.36
     प्रवासी
    0.36
    POSITIVE LOGITS
    されている
    0.43
    🤴
    0.39
    Complex
    0.38
     seems
    0.37
     由
    0.37
    复杂的
    0.37
     razlik
    0.37
     enligt
    0.37
     sembra
    0.37
     تساعد
    0.37
    Act Density 0.003%

    No Known Activations