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

    Neuronpedia

    INDEX
    Explanations

    Alcatraz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ترنت
    -0.08
    idy
    -0.08
    M
    -0.07
    EMP
    -0.07
    ;++
    -0.07
    .Inject
    -0.07
    😪
    -0.07
    _bp
    -0.07
    氇
    -0.07
    losion
    -0.07
    POSITIVE LOGITS
     Constantin
    0.08
     Jean
    0.07
    _until
    0.07
     Universal
    0.07
    partial
    0.07
     Tac
    0.07
     Physical
    0.06
     skeleton
    0.06
     WOM
    0.06
     imperial
    0.06
    Act Density 0.001%

    No Known Activations