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

    Neuronpedia

    INDEX
    Explanations

    expressing thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indignant
    0.47
     lanç
    0.47
     recast
    0.47
     concur
    0.46
     comienzo
    0.46
     ע
    0.45
     jubil
    0.45
     እነዚህ
    0.45
     admire
    0.45
     bum
    0.44
    POSITIVE LOGITS
     EXPRESS
    0.45
    Compressed
    0.45
    ೇ
    0.43
     Boutique
    0.43
    AY
    0.42
    diameter
    0.42
    was
    0.41
    ONO
    0.41
    人们
    0.40
     proteins
    0.40
    Act Density 0.018%

    No Known Activations