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

    Neuronpedia

    INDEX
    Explanations

    if, then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hvis
    0.25
    。
    0.25
    だが
    0.22
     donc
    0.20
     لكل
    0.20
     tomto
    0.20
     kuiten
    0.20
     م
    0.19
     mutta
    0.19
     poderia
    0.19
    POSITIVE LOGITS
     chances
    0.36
    それは
    0.36
    那么
    0.34
    则
    0.34
     সেটা
    0.33
     it
    0.33
     그것
    0.32
    it
    0.32
    則
    0.31
    それが
    0.30
    Act Density 0.081%

    No Known Activations