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

    Neuronpedia

    INDEX
    Explanations

    Pro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éro
    -0.07
    .uc
    -0.06
     behavioral
    -0.06
    urpose
    -0.06
    ่ใช
    -0.06
    344
    -0.06
    545
    -0.06
    ’es
    -0.06
    zbek
    -0.06
    *******
↵
    -0.06
    POSITIVE LOGITS
     بع
    0.06
    escal
    0.06
     singing
    0.06
     Rohing
    0.06
     Able
    0.06
     สำ
    0.06
    .recipe
    0.06
     λι
    0.06
     Firmware
    0.06
     شف
    0.06
    Act Density 0.010%

    No Known Activations