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

    Neuronpedia

    INDEX
    Explanations

    usage instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neoplasms
    0.86
     tees
    0.82
    ﻤ
    0.80
     invertible
    0.80
    ﺴ
    0.80
     globalMap
    0.79
     symplect
    0.78
     ব্যবস্থাপ
    0.76
    ীম
    0.76
     inmue
    0.75
    POSITIVE LOGITS
    ถ้า
    0.91
    Für
    0.90
     Czy
    0.89
     Für
    0.88
     Benutz
    0.88
     Lebih
    0.87
    power
    0.86
    point
    0.84
    Problem
    0.84
    Eine
    0.84
    Act Density 0.001%

    No Known Activations