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

    Neuronpedia

    INDEX
    Explanations

    asking for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hubiera
    0.31
     congen
    0.30
    㓡
    0.29
     rul
    0.29
     کہ
    0.28
     ultrast
    0.28
    窅
    0.28
    どんな
    0.26
     super
    0.26
    ว์
    0.25
    POSITIVE LOGITS
     me
    0.61
     yourself
    0.45
    me
    0.44
     мне
    0.42
     Yourself
    0.40
    yourself
    0.38
     আমাকে
    0.38
     نفسك
    0.37
     comigo
    0.37
    Me
    0.35
    Act Density 0.078%

    No Known Activations