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

    Neuronpedia

    INDEX
    Explanations

    derivative equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    765
    -0.07
    (port
    -0.07
    _aa
    -0.07
    	X
    -0.06
     ["
    -0.06
     Nội
    -0.06
     warp
    -0.06
    atonin
    -0.06
    -spot
    -0.06
     [
    -0.06
    POSITIVE LOGITS
    atively
    0.06
    neği
    0.06
     Tradable
    0.06
    üs
    0.06
     AHL
    0.06
    ελ
    0.06
    etimes
    0.06
     dfs
    0.06
    rowing
    0.06
    ewriter
    0.06
    Act Density 0.010%

    No Known Activations