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

    Neuronpedia

    INDEX
    Explanations

    group, ring, field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -1.16
    «,
    -1.05
    rometry
    -1.04
     himself
    -1.03
    kumpulan
    -0.96
    unds
    -0.94
    blower
    -0.93
    性は
    -0.91
     You
    -0.91
    ><
    -0.91
    POSITIVE LOGITS
    Pengertian
    1.25
    laterra
    1.18
    Tempat
    1.16
    飒
    1.16
    دانلود
    1.16
    1.13
     accredit
    1.13
    不一样的
    1.11
    zembro
    1.10
     Quels
    1.09
    Act Density 0.061%

    No Known Activations