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

    Neuronpedia

    INDEX
    Explanations

    978

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .strategy
    -0.07
    manent
    -0.07
     Popular
    -0.07
     Values
    -0.07
    oun
    -0.07
     flaw
    -0.07
     Ru
    -0.07
     folding
    -0.06
     responsibilities
    -0.06
     Dump
    -0.06
    POSITIVE LOGITS
     setImage
    0.07
    ElementType
    0.07
     liberals
    0.06
    agne
    0.06
     marginLeft
    0.06
    鐘
    0.06
    .RowHeaders
    0.06
    Registration
    0.06
    Recipes
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations