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

    Neuronpedia

    INDEX
    Explanations

    td

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     har
    -0.08
     mín
    -0.07
    SIG
    -0.07
     chỉ
    -0.07
     relacion
    -0.06
    意
    -0.06
     hemos
    -0.06
    .firebaseio
    -0.06
    ی
    -0.06
    алізації
    -0.06
    POSITIVE LOGITS
     District
    0.07
    Warehouse
    0.07
    ческий
    0.06
     Batı
    0.06
     weld
    0.06
     tonnes
    0.06
     bathtub
    0.06
    kl
    0.06
    occasion
    0.06
    ạt
    0.06
    Act Density 0.004%

    No Known Activations