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
     hrd
    -0.07
    =@"
    -0.07
     conject
    -0.07
    	ps
    -0.07
    vg
    -0.07
    analy
    -0.06
     dc
    -0.06
    .any
    -0.06
    .JWT
    -0.06
     encaps
    -0.06
    POSITIVE LOGITS
     チ
    0.06
    权
    0.06
     '/');↵
    0.06
    -mail
    0.06
    мі
    0.06
    權
    0.06
    іль
    0.06
    Invoke
    0.06
    ための
    0.06
    수
    0.06
    Act Density 0.027%

    No Known Activations