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

    Neuronpedia

    INDEX
    Explanations

    ELF header

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soglas
    0.51
    data
    0.50
    da
    0.50
    rt
    0.49
     دیکھ
    0.49
     stvarn
    0.48
    ig
    0.48
    dan
    0.48
    ﻭ
    0.48
    看
    0.46
    POSITIVE LOGITS
     Maple
    0.53
     Mule
    0.50
     Benz
    0.49
     Air
    0.48
     Dens
    0.47
     Machinery
    0.47
     Jungle
    0.47
     chain
    0.46
     Ripley
    0.46
     Fleet
    0.46
    Act Density 0.000%

    No Known Activations