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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DFS
    -0.06
    bugs
    -0.06
    _OR
    -0.06
     proč
    -0.06
    ackage
    -0.06
    تي
    -0.05
     bias
    -0.05
    chor
    -0.05
    Salary
    -0.05
     STD
    -0.05
    POSITIVE LOGITS
    .Cons
    0.07
    subplot
    0.07
     národ
    0.07
     œ
    0.07
     komple
    0.07
     subdiv
    0.07
     Shine
    0.07
     skupina
    0.06
     sel
    0.06
    .lower
    0.06
    Act Density 0.011%

    No Known Activations