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

    Neuronpedia

    INDEX
    Explanations

    English translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Garden
    0.46
     Segal
    0.42
     Approaches
    0.42
     Soybean
    0.41
     Hin
    0.40
     Bout
    0.40
     Garten
    0.39
     Estates
    0.39
     Hilton
    0.39
     approaches
    0.39
    POSITIVE LOGITS
     dialect
    0.41
    သည်
    0.39
    interpretation
    0.38
     pregn
    0.38
     commander
    0.37
    πλ
    0.37
     reç
    0.37
     دیں
    0.37
    onimo
    0.37
    থাৎ
    0.36
    Act Density 0.004%

    No Known Activations