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

    Neuronpedia

    INDEX
    Explanations

    verbs ending in ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afore
    0.52
    র
    0.52
    д
    0.52
    ലെ
    0.52
     unquestion
    0.51
     replete
    0.51
     daunting
    0.50
    ಯ್
    0.49
     dispel
    0.49
     devoured
    0.49
    POSITIVE LOGITS
     сейчас
    0.66
    ly
    0.58
    ing
    0.54
     ہیں۔
    0.52
    -
    0.50
    此时
    0.50
     इन
    0.49
    ails
    0.48
    m
    0.47
     अहिले
    0.46
    Act Density 0.282%

    No Known Activations