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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dynamics
    -0.06
    统计
    -0.06
     Come
    -0.06
    降
    -0.05
    ?\
    -0.05
    щення
    -0.05
     hydrated
    -0.05
     MyClass
    -0.05
     DEVELO
    -0.05
     organiz
    -0.05
    POSITIVE LOGITS
    (styles
    0.08
     ion
    0.07
    fty
    0.07
    lobal
    0.07
    yclerview
    0.07
    (host
    0.07
    큼
    0.07
    	duration
    0.07
     onChange
    0.07
    .phi
    0.07
    Act Density 0.004%

    No Known Activations