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

    Neuronpedia

    INDEX
    Explanations

    drop off locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ek
    1.38
    ).
    1.25
    et
    1.24
    ew
    1.24
    em
    1.23
    ec
    1.22
    en
    1.21
    est
    1.21
    t
    1.20
    ll
    1.15
    POSITIVE LOGITS
    я
    1.20
    ა
    1.05
    ی
    1.04
    یا
    1.02
    😍😍
    1.02
     Deps
    0.96
     Ellos
    0.95
     πισ
    0.95
     функ
    0.94
    Eggs
    0.94
    Act Density 0.000%

    No Known Activations