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

    Neuronpedia

    INDEX
    Explanations

    landing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ात
    0.63
    ख
    0.48
    事务
    0.48
     Brest
    0.47
    化的
    0.47
    ర్
    0.47
     diễn
    0.47
     erupted
    0.47
    ुरू
    0.46
     corroborated
    0.46
    POSITIVE LOGITS
    d
    0.50
    م
    0.49
    y
    0.49
    kerja
    0.48
    閎
    0.48
     choix
    0.47
    {{
    0.47
     laga
    0.46
    ن
    0.46
     fw
    0.46
    Act Density 0.005%

    No Known Activations