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

    Neuronpedia

    INDEX
    Explanations

    seed starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्य
    0.98
     événement
    0.80
    ہ
    0.80
    ische
    0.78
     significative
    0.77
     précisément
    0.73
     régulière
    0.73
     étro
    0.72
    काच्या
    0.72
     oraș
    0.71
    POSITIVE LOGITS
    K
    1.23
     seeds
    1.14
    Seeds
    1.14
     ]
    1.05
    F
    1.02
     Seeds
    1.00
     )
    0.98
    at
    0.96
    Seed
    0.96
     or
    0.95
    Act Density 0.006%

    No Known Activations