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

    Neuronpedia

    INDEX
    Explanations

    Essence and summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بھی
    0.98
     również
    0.94
     arī
    0.92
     fortaleza
    0.90
     पनि
    0.85
     suelen
    0.84
     rencontré
    0.84
     rencontr
    0.84
     också
    0.83
     bhi
    0.82
    POSITIVE LOGITS
     Essentially
    3.16
     Basically
    3.15
    Essentially
    3.08
     essentially
    3.02
    Basically
    3.00
     basically
    2.91
    essentially
    2.70
    basically
    2.54
     Effectively
    2.04
     Think
    1.90
    Act Density 1.067%

    No Known Activations