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

    Neuronpedia

    INDEX
    Explanations

    without precise or proper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.50
     Own
    0.45
     own
    0.43
    entor
    0.43
    ing
    0.42
     Ith
    0.42
    Del
    0.41
    N
    0.40
     став
    0.40
    UT
    0.40
    POSITIVE LOGITS
    ၊
    0.55
    、
    0.54
    ，
    0.48
     bè
    0.47
    ９
    0.47
     Transmitter
    0.47
    回路
    0.46
    PublicKey
    0.46
    廻
    0.46
    ี
    0.46
    Act Density 0.003%

    No Known Activations