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

    Neuronpedia

    INDEX
    Explanations

    existence claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doubtless
    0.35
     certainement
    0.34
     certamente
    0.33
     গেছেন
    0.33
    ੁੰ
    0.29
    alang
    0.29
     naprawdę
    0.29
     были
    0.29
     certainly
    0.28
     durchaus
    0.28
    POSITIVE LOGITS
     exists
    0.48
    exists
    0.41
     exista
    0.36
     existe
    0.36
    Existe
    0.35
    Exists
    0.34
     EXISTS
    0.34
     occurs
    0.33
     esiste
    0.33
     exist
    0.32
    Act Density 0.030%

    No Known Activations