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

    Neuronpedia

    INDEX
    Explanations

    comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WhiteBalance
    0.44
    Allora
    0.43
     διάρκ
    0.38
     algorith
    0.38
    IZONTAL
    0.37
     furlough
    0.37
    \|^{
    0.36
    饴
    0.36
    INH
    0.36
     radii
    0.36
    POSITIVE LOGITS
     Allows
    0.61
    optional
    0.57
     Enables
    0.57
     để
    0.57
     Ensures
    0.56
     Needed
    0.56
     added
    0.55
     Specify
    0.55
     ताकि
    0.55
     ensures
    0.55
    Act Density 0.028%

    No Known Activations