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

    Neuronpedia

    INDEX
    Explanations

    technology advances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lors
    1.53
    Luego
    1.49
     erstes
    1.37
     Grâce
    1.36
     montée
    1.35
    र्यंत
    1.35
     convertirse
    1.35
    attham
    1.34
     Atau
    1.34
     canzone
    1.33
    POSITIVE LOGITS
     не
    1.19
     negative
    1.11
     in
    1.11
     с
    1.09
     без
    1.08
     за
    1.06
     в
    1.05
     pin
    1.05
     male
    1.04
     populate
    1.01
    Act Density 0.000%

    No Known Activations