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

    Neuronpedia

    INDEX
    Explanations

    creators at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我们需要
    0.37
    থেকে
    0.35
    만한
    0.34
     છું
    0.34
     lLoginID
    0.34
     operandSize
    0.33
    <unused1007>
    0.33
    ရောက်
    0.32
     ');
    0.32
     जायें
    0.32
    POSITIVE LOGITS
     દ્વારા
    0.41
     في
    0.39
     द्वारा
    0.38
    ใน
    0.37
     على
    0.36
     માટે
    0.35
     в
    0.35
     via
    0.35
     during
    0.34
     برای
    0.34
    Act Density 0.135%

    No Known Activations