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

    Neuronpedia

    INDEX
    Explanations

    Documentation/Instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ddb
    -0.07
    你觉得
    -0.07
    ({});↵
    -0.07
     Quebec
    -0.07
     tes
    -0.07
    ToEnd
    -0.07
    透
    -0.07
    퓖
    -0.07
    ']↵↵↵
    -0.07
    .resp
    -0.07
    POSITIVE LOGITS
     overlays
    0.07
     laps
    0.07
     Athen
    0.07
    bab
    0.07
    \<^
    0.07
    udy
    0.07
     pizza
    0.07
    .Client
    0.07
     purs
    0.07
     aquatic
    0.07
    Act Density 0.004%

    No Known Activations