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

    Neuronpedia

    INDEX
    Explanations

    Defense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noir
    -0.08
     darkest
    -0.08
     соглас
    -0.08
     сти
    -0.08
     huy
    -0.08
     rọrun
    -0.08
    앨
    -0.08
     gaussian
    -0.08
    šie
    -0.08
     образом
    -0.08
    POSITIVE LOGITS
    院
    0.08
    ((-
    0.08
    elif
    0.08
     Georg
    0.08
     inferred
    0.07
     administration
    0.07
    mathbf
    0.07
     அமைச்ச
    0.07
    Mumbai
    0.07
    (-
    0.07
    Act Density 0.012%

    No Known Activations