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

    Neuronpedia

    INDEX
    Explanations

    however, but, furthermore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firstly
    0.44
     greats
    0.41
    selves
    0.40
     abundances
    0.40
     pierwsze
    0.39
     arranque
    0.39
     første
    0.38
    뎃
    0.38
     mixts
    0.38
    Firstly
    0.37
    POSITIVE LOGITS
     weiterer
    0.46
    さらに
    0.45
     تاہم
    0.42
     weiteren
    0.41
     தொடர்ந்து
    0.41
     dalej
    0.41
     Subsequent
    0.41
     azonban
    0.41
    ang
    0.40
     responding
    0.40
    Act Density 0.001%

    No Known Activations