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

    Neuronpedia

    INDEX
    Explanations

    UBL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dates
    -0.06
    Paris
    -0.06
    .Never
    -0.06
     kav
    -0.06
    вад
    -0.06
     vertices
    -0.06
     lion
    -0.06
    vertex
    -0.06
    Go
    -0.06
    stoi
    -0.06
    POSITIVE LOGITS
     acceptable
    0.07
     гля
    0.07
     Hern
    0.07
    OptionsMenu
    0.07
    �
    0.06
    INTERFACE
    0.06
     duel
    0.06
     �
    0.06
     Spotlight
    0.06
    .GetInstance
    0.06
    Act Density 0.001%

    No Known Activations