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

    Neuronpedia

    INDEX
    Explanations

    loses consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ات
    1.24
     kế
    1.09
     ""){
    1.05
    <0x80>
    1.02
    ї
    1.01
    انه
    1.00
    েই
    0.99
    ett
    0.99
    اء
    0.99
     greatest
    0.98
    POSITIVE LOGITS
    nueva
    1.71
     posibilidades
    1.53
     сеть
    1.50
     последствия
    1.45
    một
    1.44
     averiguar
    1.43
    stash
    1.42
     показатели
    1.40
     possibilidade
    1.40
     firsthand
    1.37
    Act Density 0.002%

    No Known Activations