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

    Neuronpedia

    INDEX
    Explanations

    xy, XY, XYZ, xyz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spaceBetween
    0.38
    絓
    0.37
     처
    0.36
    éssel
    0.36
    ælp
    0.36
     भैर
    0.36
    త్మిక
    0.36
    ைகளுக்கு
    0.34
    antai
    0.34
    섞
    0.34
    POSITIVE LOGITS
     XY
    0.57
     xy
    0.56
    XY
    0.55
    zy
    0.50
     zy
    0.47
     Zy
    0.46
    xy
    0.46
    Zy
    0.43
    entuan
    0.43
    lose
    0.42
    Act Density 0.001%

    No Known Activations