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

    Neuronpedia

    INDEX
    Explanations

    Runtime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Forbidden
    -0.06
    Inspector
    -0.06
    НО
    -0.06
    directive
    -0.06
    secure
    -0.06
    .HCM
    -0.06
    .setView
    -0.06
     shoulder
    -0.06
    .closed
    -0.06
     dessert
    -0.06
    POSITIVE LOGITS
    -added
    0.06
    ilent
    0.06
    ил
    0.06
     actu
    0.06
    纪
    0.06
     unemployed
    0.06
    .mesh
    0.06
     Allan
    0.06
     xuất
    0.06
     #####
    0.06
    Act Density 0.001%

    No Known Activations