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

    Neuronpedia

    INDEX
    Explanations

    code imports and variable assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ّ
    0.49
    妘
    0.48
    埸
    0.47
     morceaux
    0.46
     ಹಾಗ
    0.46
    ່
    0.46
    kowitz
    0.46
     Elena
    0.46
    孛
    0.46
    囘
    0.46
    POSITIVE LOGITS
     sunglasses
    0.51
    0.49
     lifecycle
    0.49
     evalu
    0.45
     electro
    0.44
     scalability
    0.43
     goldfish
    0.43
     pin
    0.43
     nalazi
    0.43
     bicycle
    0.43
    Act Density 0.001%

    No Known Activations