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

    Neuronpedia

    INDEX
    Explanations

    hope and thank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    꽉
    -0.93
     bakgrund
    -0.90
     etui
    -0.88
    Kenapa
    -0.84
     område
    -0.82
    isantes
    -0.82
    ❷
    -0.82
    mvh
    -0.80
     gamla
    -0.79
     biß
    -0.79
    POSITIVE LOGITS
     hope
    1.84
     hopefully
    1.70
     hoped
    1.59
     Hopefully
    1.57
     Hope
    1.48
    <eos>
    1.43
    Hopefully
    1.41
    Hope
    1.34
    最後まで
    1.32
     Thank
    1.26
    Act Density 0.006%

    No Known Activations