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

    Neuronpedia

    INDEX
    Explanations

    underground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lij
    -0.07
     引
    -0.06
     holy
    -0.06
    chnitt
    -0.06
     mělo
    -0.06
     lett
    -0.06
    公共
    -0.06
     sf
    -0.06
    ("@
    -0.06
    (Spring
    -0.06
    POSITIVE LOGITS
     Wheeler
    0.06
     прид
    0.06
    367
    0.06
    lanır
    0.06
    xml
    0.06
    括
    0.06
     Dur
    0.06
     tiết
    0.06
    )this
    0.06
     Willow
    0.06
    Act Density 0.000%

    No Known Activations