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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icular
    -0.07
    ために
    -0.06
    -ts
    -0.06
     isActive
    -0.06
     MVC
    -0.06
     egal
    -0.06
     ECS
    -0.06
     wicked
    -0.06
    aks
    -0.06
     yp
    -0.06
    POSITIVE LOGITS
     roku
    0.07
    {$
    0.07
     Jeff
    0.06
    _tpl
    0.06
     NEED
    0.06
     Nor
    0.06
    .shows
    0.06
     운
    0.06
    Jeff
    0.06
    Phoenix
    0.06
    Act Density 0.034%

    No Known Activations