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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Specification
    -0.07
    ρίας
    -0.07
     таб
    -0.06
    ابات
    -0.06
    па
    -0.06
    .Bold
    -0.06
    trad
    -0.06
    .Tests
    -0.06
    ]][
    -0.06
     verses
    -0.06
    POSITIVE LOGITS
    Lite
    0.07
     Tencent
    0.06
    очный
    0.06
     rest
    0.06
     justice
    0.06
     precipitation
    0.06
    /sp
    0.06
     ticaret
    0.06
    malink
    0.06
    /address
    0.06
    Act Density 0.015%

    No Known Activations