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

    Neuronpedia

    INDEX
    Explanations

    vertical lines and column references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Católica
    0.78
     ODM
    0.68
     católica
    0.68
    Catholic
    0.68
     Университе
    0.67
     Hotel
    0.66
     Catholic
    0.66
     Episcopal
    0.66
    avacanam
    0.66
     Headlines
    0.65
    POSITIVE LOGITS
     invariance
    0.81
     embeddings
    0.80
     delimiters
    0.79
     tensors
    0.77
     offsets
    0.75
     diameters
    0.75
     polynomials
    0.73
     scalars
    0.73
     inhomogeneity
    0.73
     widths
    0.72
    Act Density 0.001%

    No Known Activations