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

    Neuronpedia

    INDEX
    Explanations

    tribal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     models
    -0.07
     Dx
    -0.07
    tool
    -0.07
     Models
    -0.06
    */↵↵
    -0.06
    results
    -0.06
    cyan
    -0.06
    LEAN
    -0.06
    eros
    -0.06
    ”.↵↵
    -0.06
    POSITIVE LOGITS
     tribunal
    0.09
     Tribunal
    0.08
    (IB
    0.07
     TBranch
    0.07
     Tamb
    0.07
     tribal
    0.07
     Trib
    0.07
    \Twig
    0.06
     Rib
    0.06
    traction
    0.06
    Act Density 0.005%

    No Known Activations