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

    Neuronpedia

    INDEX
    Explanations

    kosher

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _user
    -0.06
     Move
    -0.06
    Editing
    -0.06
     úspě
    -0.06
    .initializeApp
    -0.06
    델
    -0.06
    yper
    -0.06
    (Node
    -0.06
    (level
    -0.06
     Alignment
    -0.06
    POSITIVE LOGITS
    очного
    0.08
     coop
    0.07
     ControllerBase
    0.07
     prospect
    0.07
     quo
    0.07
     レ
    0.07
    instead
    0.06
     PCI
    0.06
    кість
    0.06
     beforeEach
    0.06
    Act Density 0.006%

    No Known Activations