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

    Neuronpedia

    INDEX
    Explanations

    Hotel reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    information
    -0.07
     frustrations
    -0.07
     Creation
    -0.06
    SCRIBE
    -0.06
     radial
    -0.06
    ites
    -0.06
    キュ
    -0.06
    iel
    -0.06
     Armen
    -0.06
    िल
    -0.06
    POSITIVE LOGITS
    >>)
    0.06
    посеред
    0.06
    �
    0.06
    Distinct
    0.06
     Comparator
    0.06
     свящ
    0.06
    ManagerInterface
    0.06
    tableFuture
    0.06
     cartridge
    0.06
    оці
    0.06
    Act Density 0.027%

    No Known Activations