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

    Neuronpedia

    INDEX
    Explanations

    I/we followed by informal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Additionally
    0.63
    此外
    0.55
    较为
    0.51
     additional
    0.51
     Additionally
    0.49
    additional
    0.49
    Additional
    0.48
     एवं
    0.47
    Furthermore
    0.46
     অপরদিকে
    0.46
    POSITIVE LOGITS
     didn
    0.92
     dunno
    0.86
     gotta
    0.84
     kinda
    0.80
     probably
    0.79
     gonna
    0.78
     hadn
    0.77
     couldn
    0.77
     ain
    0.77
     wasn
    0.77
    Act Density 0.293%

    No Known Activations