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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ith
    -0.06
    (currentUser
    -0.06
    mesi
    -0.06
     đậu
    -0.06
    /example
    -0.06
    [P
    -0.06
     بار
    -0.06
     války
    -0.06
    488
    -0.06
     Mk
    -0.06
    POSITIVE LOGITS
     heroic
    0.07
    Refs
    0.06
     bullshit
    0.06
     Null
    0.06
     \<^
    0.06
    ється
    0.06
     сахар
    0.06
     HeaderComponent
    0.06
     было
    0.06
     accompanying
    0.06
    Act Density 0.104%

    No Known Activations