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

    Neuronpedia

    INDEX
    Explanations

    listing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possa
    0.45
     tweaks
    0.43
    苣
    0.42
     swaps
    0.42
     मैचों
    0.42
    ちゃんと
    0.42
     underserved
    0.41
     হারানোর
    0.41
     pueda
    0.41
     సినిమాలు
    0.41
    POSITIVE LOGITS
    Beautiful
    0.84
     beautiful
    0.84
    beautiful
    0.84
     Beautiful
    0.79
     magnificent
    0.71
     அற்புதமான
    0.70
     stunning
    0.68
     prachtige
    0.68
     Stunning
    0.68
     bellissimo
    0.66
    Act Density 0.002%

    No Known Activations