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

    Neuronpedia

    INDEX
    Explanations

    testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theta
    -0.07
    Salt
    -0.07
    lip
    -0.06
    ะแนน
    -0.06
     мали
    -0.06
    ük
    -0.06
    erc
    -0.06
    .touches
    -0.06
    />
    -0.06
    views
    -0.06
    POSITIVE LOGITS
     umění
    0.07
    ağa
    0.06
     visto
    0.06
     dağ
    0.06
    丁
    0.06
    rå
    0.06
    ={`/
    0.06
     engr
    0.06
    dependence
    0.06
    让
    0.06
    Act Density 0.323%

    No Known Activations