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

    Neuronpedia

    INDEX
    Explanations

    providing "1"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    本セット
    1.33
    이
    1.30
    ities
    1.25
    tenths
    1.25
    ging
    1.24
     sc
    1.23
    ges
    1.22
    tia
    1.21
    தனை
    1.18
     puluh
    1.10
    POSITIVE LOGITS
    st
    2.52
    ️⃣
    2.26
    ल
    2.16
    р
    2.06
    ⃙
    1.93
    ⃣
    1.90
    dbjc
    1.89
    xbet
    1.86
    на
    1.85
    л
    1.81
    Act Density 0.282%

    No Known Activations