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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sectors
    -0.07
    測
    -0.07
    …but
    -0.06
    Md
    -0.06
    :mm
    -0.06
     xy
    -0.06
     gereken
    -0.06
     důvodu
    -0.06
    stro
    -0.06
     среди
    -0.06
    POSITIVE LOGITS
     Marshall
    0.06
     معد
    0.06
     Wolfe
    0.06
     remember
    0.06
    /update
    0.06
    _does
    0.06
     comes
    0.06
    :self
    0.06
     Palm
    0.06
     Sn
    0.05
    Act Density 0.008%

    No Known Activations