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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usive
    -0.06
     qualifier
    -0.06
    eland
    -0.06
     बन
    -0.06
     atroc
    -0.06
    561
    -0.06
    entication
    -0.06
     动
    -0.06
     mortgage
    -0.06
    ONGL
    -0.06
    POSITIVE LOGITS
    .Footer
    0.08
     αγ
    0.06
    ніп
    0.06
    :[[
    0.06
    €€
    0.06
    (sound
    0.06
     Willi
    0.06
     WIFI
    0.06
    รอบ
    0.06
    tems
    0.06
    Act Density 0.017%

    No Known Activations