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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     co
    -0.07
     Shore
    -0.07
     Co
    -0.07
     shower
    -0.06
    soon
    -0.06
     driv
    -0.06
    anne
    -0.06
     anti
    -0.06
      ↵    ↵
    -0.06
     пля
    -0.06
    POSITIVE LOGITS
    UpDown
    0.07
    ốn
    0.07
    entai
    0.07
     황
    0.06
    [])↵
    0.06
    acobian
    0.06
     senha
    0.06
    productName
    0.06
    oriously
    0.06
     DFA
    0.06
    Act Density 0.000%

    No Known Activations