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

    Neuronpedia

    INDEX
    Explanations

    reconstruct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mellitus
    -0.09
    udah
    -0.08
    tube
    -0.08
     tubes
    -0.08
    imonio
    -0.07
    ivar
    -0.07
    wick
    -0.07
    ekan
    -0.07
     tube
    -0.07
    Subsystem
    -0.07
    POSITIVE LOGITS
     reconstruct
    0.11
     reconstruction
    0.09
     reconstructed
    0.09
     reconstru
    0.09
     Reconstruction
    0.08
     rekon
    0.08
     Yuk
    0.08
     recreate
    0.08
     निर्म
    0.08
     recre
    0.08
    Act Density 0.010%

    No Known Activations