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

    Neuronpedia

    INDEX
    Explanations

    ratings and scales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ૩
    0.50
    BleStatus
    0.46
     ٣
    0.42
    在那
    0.40
     ३
    0.40
     столь
    0.38
    ３
    0.38
     भले
    0.38
    Tiles
    0.37
     ৩
    0.37
    POSITIVE LOGITS
     corresponds
    0.50
    the
    0.45
    即
    0.45
    representing
    0.45
     corresponde
    0.45
    corresponding
    0.45
     correspondant
    0.45
     correspondiente
    0.44
    ️⃣
    0.44
     the
    0.44
    Act Density 0.022%

    No Known Activations