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

    Neuronpedia

    INDEX
    Explanations

    no or nothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mp
    0.95
    ep
    0.95
     multiplets
    0.93
    um
    0.92
    m
    0.89
    ec
    0.88
    yc
    0.88
    yr
    0.87
    ek
    0.86
    র
    0.85
    POSITIVE LOGITS
     불구하고
    1.14
    υτό
    1.05
    дна
    1.04
     entanto
    1.03
     alcuna
    1.03
     alcun
    0.96
    resnet
    0.95
    ᅭ
    0.92
    0.91
    𝘩
    0.90
    Act Density 0.294%

    No Known Activations