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

    Neuronpedia

    INDEX
    Explanations

    pronoun + verb/auxiliary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equaling
    0.36
     pennies
    0.35
     exceeds
    0.33
    صیٰ
    0.33
     (>
    0.32
     گئی۔
    0.31
     সময়ই
    0.31
     महीने
    0.31
     Bây
    0.31
     UNNEEDED
    0.31
    POSITIVE LOGITS
     de
    0.42
    histoire
    0.35
     மேலும்
    0.33
    ט
    0.33
    The
    0.32
    É
    0.31
    で
    0.31
    ompok
    0.30
    阿
    0.30
    이
    0.30
    Act Density 0.216%

    No Known Activations