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

    Neuronpedia

    INDEX
    Explanations

    spatial positions and coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InCM
    0.43
     Perempuan
    0.39
     proguardFiles
    0.38
     Mga
    0.38
    惣
    0.38
     femenino
    0.37
     Ae
    0.35
     delim
    0.35
     condem
    0.35
     xlink
    0.35
    POSITIVE LOGITS
    positions
    0.54
    position
    0.50
    locations
    0.48
     positions
    0.48
     locations
    0.47
     location
    0.45
    location
    0.45
    bourne
    0.45
     position
    0.44
    Offset
    0.44
    Act Density 0.130%

    No Known Activations