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

    Neuronpedia

    INDEX
    Explanations

    Time-consuming tasks/projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betrayal
    -0.06
    raig
    -0.06
    .GenerationType
    -0.06
    Unity
    -0.06
    НІ
    -0.06
     برگز
    -0.06
    <i
    -0.06
     UNITY
    -0.06
    enade
    -0.06
     바라
    -0.06
    POSITIVE LOGITS
    采用
    0.06
     Account
    0.06
     glove
    0.06
     newInstance
    0.06
     corresponding
    0.06
     court
    0.06
    sigma
    0.06
    %
↵
    0.06
    itamin
    0.06
    anja
    0.06
    Act Density 0.161%

    No Known Activations