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

    Neuronpedia

    INDEX
    Explanations

    linking conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    および
    0.44
     =>
    0.43
     及
    0.39
    及
    0.39
     Rồi
    0.38
     diikuti
    0.38
    Analy
    0.38
     以及
    0.38
    그리고
    0.37
    ，
    0.37
    POSITIVE LOGITS
    ppure
    0.57
     although
    0.55
     importantly
    0.54
     ponieważ
    0.51
     rightly
    0.49
     crucially
    0.49
     поскольку
    0.47
     unlike
    0.45
     interestingly
    0.45
     conversely
    0.45
    Act Density 0.018%

    No Known Activations