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

    Neuronpedia

    INDEX
    Explanations

    spreading and expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मुठभे
    0.71
     подве
    0.68
     Intervals
    0.64
    ኦ
    0.64
    投げ
    0.64
     apartado
    0.63
     susp
    0.63
     duelo
    0.63
     Lament
    0.62
     памяти
    0.62
    POSITIVE LOGITS
     spreading
    2.35
     spread
    2.30
     expansion
    2.17
     expanding
    2.15
     expand
    2.12
     распростра
    2.05
    spreading
    2.04
    Expansion
    2.01
     Expansion
    2.00
    expansion
    1.99
    Act Density 0.248%

    No Known Activations