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

    Neuronpedia

    INDEX
    Explanations

    resource performance overhead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ও
    0.49
     departure
    0.46
     আইনে
    0.44
    會
    0.43
    trp
    0.42
     altitudes
    0.42
    江苏
    0.42
    Department
    0.42
    重生
    0.41
    会
    0.41
    POSITIVE LOGITS
    aga
    0.52
    ite
    0.52
    aya
    0.51
    otiti
    0.51
    respon
    0.51
    ahaha
    0.50
    imba
    0.50
    organized
    0.49
    iteten
    0.48
    ræ
    0.47
    Act Density 0.000%

    No Known Activations