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

    Neuronpedia

    INDEX
    Explanations

    avoiding specific verb forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人們
    0.51
     Ashanti
    0.48
    ἷ
    0.47
     धूप
    0.44
    ப்பிரிக்க
    0.44
    朋友們
    0.44
    Button
    0.44
     outs
    0.44
     домаћин
    0.44
    maket
    0.44
    POSITIVE LOGITS
    ablo
    0.47
    vede
    0.44
    وف
    0.43
    ef
    0.43
    产生
    0.41
    駄
    0.41
     wretched
    0.41
    +
    0.40
     lauf
    0.39
    程
    0.39
    Act Density 0.002%

    No Known Activations