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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cemetery
    -0.08
     Daily
    -0.07
    619
    -0.07
     DRM
    -0.06
     caves
    -0.06
    油
    -0.06
    Daily
    -0.06
    (rel
    -0.06
     Ally
    -0.06
     loosely
    -0.06
    POSITIVE LOGITS
     resurrection
    0.07
     Reports
    0.07
    postgres
    0.07
    ignon
    0.07
     fifty
    0.07
     crumbling
    0.07
    sessions
    0.06
    sortable
    0.06
     персп
    0.06
    ----------↵
    0.06
    Act Density 0.003%

    No Known Activations