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

    Neuronpedia

    INDEX
    Explanations

    favorite hobby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.24
    ۔
    0.23
    ।
    0.23
    ។
    0.23
     elution
    0.22
    🔸
    0.21
     ہے۔
    0.21
     રંગ
    0.21
     acquittal
    0.20
     সিদ্ধান্ত
    0.20
    POSITIVE LOGITS
    z
    0.26
    h
    0.25
    k
    0.24
     philosophers
    0.20
    f
    0.20
    w
    0.19
    u
    0.19
    రీలు
    0.19
    j
    0.19
    x
    0.18
    Act Density 0.775%

    No Known Activations