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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cherche
    -0.07
     echoes
    -0.07
     ways
    -0.07
    pick
    -0.07
     Reflection
    -0.07
     tercer
    -0.07
    กราคม
    -0.07
     Sokol
    -0.07
     Ahead
    -0.07
     Drawing
    -0.07
    POSITIVE LOGITS
    OfWork
    0.06
    HashSet
    0.06
    Permission
    0.06
    (.
    0.06
    urable
    0.06
     Workflow
    0.06
    _instances
    0.05
    丰
    0.05
    燃
    0.05
    @GeneratedValue
    0.05
    Act Density 0.009%

    No Known Activations