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

    Neuronpedia

    INDEX
    Explanations

    differentiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    95
    -0.07
     Liu
    -0.06
    716
    -0.06
    _list
    -0.06
     pumps
    -0.06
    Lu
    -0.06
    ChangeEvent
    -0.06
     churches
    -0.06
     shut
    -0.06
     pump
    -0.06
    POSITIVE LOGITS
     differentiation
    0.08
     differentiated
    0.08
    off
    0.08
     Anders
    0.08
     differentiate
    0.08
     ether
    0.08
     víde
    0.07
    .Then
    0.07
     DIC
    0.07
    ργ
    0.07
    Act Density 0.006%

    No Known Activations