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

    Neuronpedia

    INDEX
    Explanations

    -h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olarity
    -0.07
     Sas
    -0.07
     collagen
    -0.07
    انية
    -0.07
    잽
    -0.07
    רוצה
    -0.07
     Orthodox
    -0.06
    amic
    -0.06
    ilan
    -0.06
    롼
    -0.06
    POSITIVE LOGITS
     lå
    0.08
     tempt
    0.08
     которой
    0.07
     errmsg
    0.07
     dw
    0.07
    脱
    0.07
    .transport
    0.06
    并不多
    0.06
     Locations
    0.06
     exporters
    0.06
    Act Density 0.008%

    No Known Activations