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

    Neuronpedia

    INDEX
    Explanations

    descriptive words following contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    龊
    0.39
     দুর
    0.39
     እር
    0.37
    គ្រ
    0.37
    保
    0.37
     workout
    0.37
    eyer
    0.37
    evu
    0.37
    usik
    0.37
     shifts
    0.36
    POSITIVE LOGITS
    loé
    0.42
    仄
    0.40
    toFixed
    0.39
    niku
    0.39
     Solo
    0.38
    忒
    0.38
     soloist
    0.38
     solo
    0.37
    ζε
    0.37
     Loy
    0.37
    Act Density 0.000%

    No Known Activations