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

    Neuronpedia

    INDEX
    Explanations

    Rutgers University, variable Y assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     repetir
    0.47
     aplica
    0.47
    രീ
    0.43
     rocky
    0.43
    回答
    0.42
     on
    0.42
     Isles
    0.42
     emailing
    0.42
    нит
    0.41
    動
    0.41
    POSITIVE LOGITS
    ufficient
    0.48
     മതി
    0.48
    赃
    0.46
    廪
    0.46
    netz
    0.44
    dataReader
    0.44
    secrets
    0.44
    ρίς
    0.43
    akkha
    0.43
     heresy
    0.43
    Act Density 0.001%

    No Known Activations