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

    Neuronpedia

    INDEX
    Explanations

    poetic and descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilizzando
    0.50
     एस
    0.48
     utilisons
    0.46
     adicionales
    0.46
     menggunakan
    0.45
     utilizzare
    0.45
     usando
    0.44
     utilizando
    0.43
     penggunaan
    0.43
     chicas
    0.43
    POSITIVE LOGITS
     sorrow
    0.44
     trembling
    0.39
     Nietzsche
    0.38
     melancholy
    0.38
     poet
    0.37
     Eternity
    0.37
     Sorrow
    0.36
     innumerable
    0.36
     scorn
    0.36
     centuries
    0.35
    Act Density 0.626%

    No Known Activations