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

    Neuronpedia

    INDEX
    Explanations

    narrow down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    י
    1.68
    িয়ে
    1.44
    きた
    1.38
     tumultuous
    1.38
    いろんな
    1.34
    م
    1.30
    ك
    1.25
    ל
    1.24
    <0x80>
    1.22
    o
    1.19
    POSITIVE LOGITS
    ate
    1.33
    ata
    1.29
    ę
    1.27
     няко
    1.25
    ąz
    1.23
    да
    1.23
    пре
    1.20
    ineries
    1.19
    ări
    1.17
    ान
    1.16
    Act Density 0.112%

    No Known Activations