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

    Neuronpedia

    INDEX
    Explanations

    notebooks and journals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    poste
    0.44
    pca
    0.44
    rera
    0.43
    afa
    0.43
    nfasis
    0.43
    acidad
    0.42
    ausa
    0.42
    soup
    0.42
    fcast
    0.41
    apikey
    0.41
    POSITIVE LOGITS
     pages
    0.98
     book
    0.92
     notebook
    0.90
     boek
    0.89
     libro
    0.83
     Pages
    0.82
     notebooks
    0.81
     pagine
    0.80
     livro
    0.78
     книга
    0.77
    Act Density 0.072%

    No Known Activations