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

    Neuronpedia

    INDEX
    Explanations

    verbs ending ING or ED

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Yeni
    0.41
     सक्षम
    0.38
    Tart
    0.38
    ECTOR
    0.37
    Per
    0.36
    Фи
    0.36
    Campaign
    0.35
    신
    0.35
    Ï
    0.35
    Tar
    0.34
    POSITIVE LOGITS
     heed
    0.46
     métodos
    0.44
    ؓ
    0.41
     Chom
    0.41
     chá
    0.41
     metodi
    0.40
     brasile
    0.39
     cli
    0.39
    ⽅
    0.39
     adoles
    0.38
    Act Density 0.005%

    No Known Activations