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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الأر
    -0.07
    .nb
    -0.07
    رد
    -0.07
     fuel
    -0.07
     자유
    -0.07
     Bez
    -0.07
    _comments
    -0.06
    ocurrency
    -0.06
     yaw
    -0.06
    شرع
    -0.06
    POSITIVE LOGITS
    ==========↵
    0.07
    .');↵
    0.07
     !!!
    0.07
    蔬
    0.07
    '],↵↵
    0.07
    .links
    0.07
    .');↵↵
    0.07
    䠼
    0.07
    PIN
    0.07
    ]];
    0.07
    Act Density 0.007%

    No Known Activations